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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-LLAMASCOPE-RES-32K
    6. 13376
    Prev
    Next
    INDEX
    Explanations

    data related to historical census entries and individual life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issan
    -0.15
    ewe
    -0.15
    ecies
    -0.15
    ectl
    -0.14
    Æ°á»Ľ
    -0.14
    vod
    -0.14
    ê²łëĭ¤
    -0.14
    errat
    -0.13
    oder
    -0.13
     thứ
    -0.13
    POSITIVE LOGITS
    iddle
    0.15
    _snapshot
    0.14
    733
    0.14
    sten
    0.14
    /commons
    0.14
     household
    0.14
    izr
    0.14
     deser
    0.14
     interviewer
    0.14
    िर
    0.13
    Activations Density 0.021%

    No Known Activations