© 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. 2-LLAMASCOPE-RES-32K
    11. 28049
    Prev
    Next
    INDEX
    Explanations

    descriptions and expressions of feelings and sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ale
    -0.14
    lef
    -0.14
     seams
    -0.14
    .getBytes
    -0.14
     fo
    -0.14
     Anton
    -0.14
    Ale
    -0.14
    fields
    -0.14
    aran
    -0.13
     promot
    -0.13
    POSITIVE LOGITS
     xlink
    0.16
    елÑİ
    0.15
    achen
    0.15
    ALSE
    0.14
    aight
    0.14
    982
    0.14
    ikler
    0.14
    ượng
    0.13
    totals
    0.13
    inkle
    0.13
    Activations Density 0.014%

    No Known Activations