© 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. 30-LLAMASCOPE-RES-32K
    6. 23675
    Prev
    Next
    INDEX
    Explanations

    references to the occurrence or relevance of key concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARGIN
    -0.18
    --
    -0.15
    ason
    -0.14
    HEST
    -0.14
    ÑĢÑıд
    -0.14
    isko
    -0.14
    ologic
    -0.14
    isay
    -0.14
    sen
    -0.14
    åħ¶
    -0.14
    POSITIVE LOGITS
     bike
    0.19
     rider
    0.18
     riders
    0.18
     —
    0.17
     —↵
    0.17
     bicy
    0.16
     Streets
    0.16
     Bike
    0.16
     bikes
    0.16
     Bis
    0.16
    Activations Density 0.000%

    No Known Activations