© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 11433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating types of categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elli
    -0.14
    330
    -0.14
    ieber
    -0.14
     Timber
    -0.14
    tim
    -0.13
    iber
    -0.13
    unger
    -0.13
     both
    -0.12
    pur
    -0.12
    gens
    -0.12
    POSITIVE LOGITS
    rome
    0.15
    xec
    0.14
    ÃŃž
    0.14
    ichert
    0.14
     müc
    0.14
    Enemies
    0.13
     Provid
    0.13
    coverage
    0.12
    TION
    0.12
    Writes
    0.12
    Activations Density 0.070%

    No Known Activations