© 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. 17-LLAMASCOPE-RES-32K
    11. 26918
    Prev
    Next
    INDEX
    Explanations

    frequent nouns and punctuation that indicate a high level of detail or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rencontres
    -0.15
     trough
    -0.15
    stro
    -0.15
    &action
    -0.15
     มห
    -0.15
    leine
    -0.14
     retail
    -0.14
    ahren
    -0.14
    اÙĨÛĮ
    -0.14
     Howell
    -0.14
    POSITIVE LOGITS
    iform
    0.17
    aps
    0.16
    çµ
    0.15
    $MESS
    0.15
    à¹ĥ
    0.14
    illy
    0.14
    bo
    0.14
    .EOF
    0.14
    467
    0.14
    DX
    0.13
    Activations Density 0.001%

    No Known Activations