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. 5-LLAMASCOPE-RES-32K
    6. 25077
    Prev
    Next
    INDEX
    Explanations

    instances of the word "have" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eko
    -0.16
    ugh
    -0.15
    dehy
    -0.15
    оги
    -0.15
    illing
    -0.14
     Bundesliga
    -0.13
    "><!--
    -0.13
    ield
    -0.13
     branch
    -0.13
     horse
    -0.13
    POSITIVE LOGITS
     phạm
    0.17
    /cms
    0.17
    SEA
    0.16
    ÅĻad
    0.16
    .libs
    0.15
    ë²Į
    0.14
    иÑī
    0.14
    ÅĻeh
    0.14
    alnız
    0.14
    xico
    0.14
    Activations Density 0.057%

    No Known Activations