© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 4352
    Prev
    Next
    INDEX
    Explanations

    quoted speech and attributions related to personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸Ļà¸Ń
    -0.15
    elsif
    -0.15
    Ì
    -0.14
    ulis
    -0.14
    кÑĥл
    -0.13
     Kou
    -0.13
    _pending
    -0.13
    able
    -0.13
     Reyes
    -0.13
    füg
    -0.13
    POSITIVE LOGITS
    nech
    0.14
    illet
    0.14
    rops
    0.14
    agos
    0.14
     Wonder
    0.14
    éľŀ
    0.13
    ãĥ³ãĥĩ
    0.13
    _pref
    0.13
    065
    0.13
    .bulk
    0.13
    Activations Density 0.451%

    No Known Activations