© 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. 27-LLAMASCOPE-RES-32K
    11. 10307
    Prev
    Next
    INDEX
    Explanations

    references to various scientific and academic disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Deg
    -0.15
    lander
    -0.15
    :uint
    -0.14
    iT
    -0.14
     treff
    -0.14
    _extended
    -0.14
    ÎŃÏģα
    -0.14
    anged
    -0.14
    γή
    -0.14
    minated
    -0.14
    POSITIVE LOGITS
    ologie
    0.19
    ismus
    0.18
    irsch
    0.17
    alien
    0.17
    ifik
    0.17
    amarin
    0.16
    jekt
    0.16
    okrat
    0.16
    onen
    0.16
     und
    0.16
    Activations Density 0.164%

    No Known Activations