© 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. 8-LLAMASCOPE-RES-32K
    11. 29909
    Prev
    Next
    INDEX
    Explanations

    terms related to relationships and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anou
    -0.17
    ainless
    -0.15
    .StackTrace
    -0.14
    eview
    -0.14
     bail
    -0.14
     Huyá»ĩn
    -0.14
     ür
    -0.13
    estruction
    -0.13
     Stout
    -0.13
     tender
    -0.13
    POSITIVE LOGITS
    engin
    0.19
    imens
    0.15
    urons
    0.15
    ascar
    0.14
    uria
    0.14
    دار
    0.14
    illum
    0.14
    awe
    0.14
    atrix
    0.14
    alim
    0.14
    Activations Density 0.854%

    No Known Activations