© 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. 11694
    Prev
    Next
    INDEX
    Explanations

    connections to music, films, and their emotional or thematic elements

    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
    FieldValue
    -0.16
    sez
    -0.15
    uder
    -0.14
     ÙħÛĮÚ©
    -0.13
    AZY
    -0.13
    ryn
    -0.13
    TAIL
    -0.13
    IFO
    -0.13
    .Aggressive
    -0.13
    seau
    -0.13
    POSITIVE LOGITS
    enc
    0.14
    atoria
    0.14
    alm
    0.13
     .
    0.13
    ieg
    0.13
     du
    0.12
    ince
    0.12
    imary
    0.12
    enger
    0.12
    0.12
    Activations Density 0.053%

    No Known Activations