© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 3902
    Prev
    Next
    INDEX
    Explanations

    phrases related to descriptions of items, likely focusing on categories or attributes associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einen
    -0.26
     keinen
    -0.24
     diesen
    -0.24
    лаÑĤÑĥ
    -0.23
    owej
    -0.23
     neuen
    -0.22
     den
    -0.21
    osti
    -0.21
     deutschen
    -0.21
    Ñģкой
    -0.21
    POSITIVE LOGITS
    еннаÑı
    0.35
    ÑİÑīаÑı
    0.34
    алÑĮнаÑı
    0.33
    наÑı
    0.33
    оваÑı
    0.33
    ÑģкаÑı
    0.33
    ÑĩеÑģкаÑı
    0.32
    каÑı
    0.32
    иÑĩеÑģкаÑı
    0.31
    ÑģÑĤвеннаÑı
    0.30
    Activations Density 0.047%

    No Known Activations