© 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. 30-LLAMASCOPE-RES-32K
    6. 12357
    Prev
    Next
    INDEX
    Explanations

    references to social and emotional concepts, as well as mentions of educational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $MESS
    -0.14
     jadx
    -0.13
    apat
    -0.12
    esiyle
    -0.12
    itel
    -0.11
    esine
    -0.11
     ><?
    -0.11
    anke
    -0.11
    ynom
    -0.11
    елеÑĦон
    -0.10
    POSITIVE LOGITS
     em
    1.24
     Em
    1.23
    -em
    1.13
    Em
    1.12
    em
    1.08
    _em
    1.03
    .em
    0.98
     EM
    0.97
    (em
    0.89
    EM
    0.88
    Activations Density 0.682%

    No Known Activations