© 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. 23-LLAMASCOPE-RES-32K
    11. 11386
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Doug" or "Douglas" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    san
    -0.17
    uco
    -0.17
    egend
    -0.16
     alternate
    -0.16
    song
    -0.15
     Alternate
    -0.15
    onic
    -0.14
    ers
    -0.14
    olley
    -0.14
    oultry
    -0.14
    POSITIVE LOGITS
    lass
    0.36
    лаÑģ
    0.28
    LAS
    0.28
    glas
    0.23
    ernaut
    0.20
    las
    0.20
    last
    0.18
    nut
    0.16
     fir
    0.16
    blas
    0.16
    Activations Density 0.004%

    No Known Activations