© 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. 8-LLAMASCOPE-RES-32K
    6. 25137
    Prev
    Next
    INDEX
    Explanations

    instances of the word "write" and its variations, indicating a focus on writing-related actions

    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
    /out
    -0.17
    wel
    -0.17
    riter
    -0.16
    h
    -0.15
    wards
    -0.15
    692
    -0.15
    921
    -0.15
    ground
    -0.14
    757
    -0.14
    utom
    -0.14
    POSITIVE LOGITS
    коÑĤ
    0.17
     tắt
    0.16
    undef
    0.16
    æ¡£
    0.16
    üns
    0.15
    addon
    0.15
    offsetof
    0.15
    ystack
    0.14
    zes
    0.14
    oldemort
    0.14
    Activations Density 0.096%

    No Known Activations