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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 28602
    Prev
    Next
    INDEX
    Explanations

    contact information and administrative details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ứ
    -0.15
     via
    -0.15
     Troy
    -0.15
     based
    -0.14
    ANCH
    -0.14
    ÚĨ
    -0.14
     Observer
    -0.14
    ips
    -0.13
     pe
    -0.13
    oge
    -0.13
    POSITIVE LOGITS
     Fax
    0.29
    Fax
    0.27
     fax
    0.24
    fax
    0.22
    DX
    0.17
    ifax
    0.15
    ãĥ«ãĤ¯
    0.15
    arella
    0.15
    opus
    0.14
    enville
    0.14
    Activations Density 0.047%

    No Known Activations