© 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. 21311
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and its consequences

    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
    ãĤ«ãĥĨ
    -0.16
    abor
    -0.14
    enty
    -0.14
    umbs
    -0.14
    Exited
    -0.13
    ighth
    -0.13
    AMS
    -0.13
     onResponse
    -0.13
    IV
    -0.13
    .forRoot
    -0.13
    POSITIVE LOGITS
     bite
    0.28
     haunt
    0.26
    cost
    0.26
     cost
    0.25
     costing
    0.24
    bite
    0.23
     COST
    0.22
     Cost
    0.22
     bites
    0.22
     costs
    0.21
    Activations Density 0.158%

    No Known Activations