Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 14222
    Prev
    Next
    INDEX
    Explanations

    mentions of errors and political affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±±å¸Ĥ
    -0.19
    yat
    -0.16
    agus
    -0.15
     à¤ĸड
    -0.14
    äh
    -0.14
     Lon
    -0.14
    ATO
    -0.14
    olan
    -0.14
    наÑĢÑĥж
    -0.14
    dispatch
    -0.13
    POSITIVE LOGITS
     ones
    0.15
    oser
    0.14
     locality
    0.14
    uario
    0.13
     Curt
    0.13
    à¸Ļวà¸Ļ
    0.13
     Perr
    0.13
    ippo
    0.13
    OSP
    0.13
    orsk
    0.13
    Activations Density 0.123%

    No Known Activations