© 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. 25-LLAMASCOPE-RES-32K
    6. 10955
    Prev
    Next
    INDEX
    Explanations

    references to the collection of information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conti
    -0.14
    dorf
    -0.12
    .timeScale
    -0.12
    noinspection
    -0.12
    stor
    -0.12
    :UIButtonTypeCustom
    -0.11
    _DEBUG
    -0.11
    erring
    -0.11
    910
    -0.11
    505
    -0.11
    POSITIVE LOGITS
     information
    1.11
    information
    0.91
     info
    0.88
    ä¿¡æģ¯
    0.83
     Information
    0.78
    Information
    0.76
    -information
    0.75
     información
    0.75
     informations
    0.74
     INFORMATION
    0.73
    Activations Density 0.822%

    No Known Activations