© 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. 23-LLAMASCOPE-RES-32K
    11. 27986
    Prev
    Next
    INDEX
    Explanations

    mentions of "crew" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cz
    -0.16
    steen
    -0.15
    ../
    -0.15
    grund
    -0.15
    relude
    -0.15
    roscope
    -0.15
    .creation
    -0.14
     Mig
    -0.14
    ation
    -0.14
    uj
    -0.14
    POSITIVE LOGITS
    members
    0.36
    member
    0.31
     members
    0.26
    neck
    0.24
    ed
    0.23
    -member
    0.23
     member
    0.23
    mates
    0.21
    _member
    0.21
    ster
    0.20
    Activations Density 0.009%

    No Known Activations