© 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. 16214
    Prev
    Next
    INDEX
    Explanations

    frequent nouns and pronouns, suggesting a focus on identifying relationships between subjects and their actions or characteristics

    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
    tight
    -0.15
    atos
    -0.15
    imeo
    -0.14
     antim
    -0.14
    chos
    -0.14
     innocent
    -0.14
    anno
    -0.14
    нг
    -0.14
     Seymour
    -0.14
    /Foundation
    -0.14
    POSITIVE LOGITS
    ibil
    0.16
    ird
    0.16
    isson
    0.15
    Equality
    0.14
    ilton
    0.14
    aggi
    0.14
     svens
    0.14
    .pix
    0.14
     çĿ
    0.14
    çĿ
    0.14
    Activations Density 0.030%

    No Known Activations