© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 6373
    Prev
    Next
    INDEX
    Explanations

    indicative patterns or specific sequences in personal names and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ót
    -0.15
    vik
    -0.15
    ırak
    -0.15
    erot
    -0.15
    FRING
    -0.14
    untime
    -0.14
    inki
    -0.14
    _firestore
    -0.14
    ifle
    -0.14
    kate
    -0.14
    POSITIVE LOGITS
    .biz
    0.19
     N
    0.16
    egis
    0.14
     Bez
    0.14
     Tan
    0.14
    κά
    0.13
     Bos
    0.13
     Dod
    0.13
     rub
    0.13
     Lud
    0.13
    Activations Density 0.184%

    No Known Activations