© 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. 10-LLAMASCOPE-RES-32K
    11. 3459
    Prev
    Next
    INDEX
    Explanations

    discussions about societal or health-related challenges and their implications

    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
     é£
    -0.15
    itä
    -0.15
    elia
    -0.14
     çħ
    -0.14
    ãĥ³ãĥij
    -0.14
     Hood
    -0.14
    łģ
    -0.14
    aku
    -0.13
    idis
    -0.13
    yg
    -0.13
    POSITIVE LOGITS
    .statusText
    0.17
    ernel
    0.15
    CX
    0.14
     togg
    0.14
    .Messaging
    0.14
    607
    0.14
     INTERRUPTION
    0.14
    ernels
    0.13
     tun
    0.13
    _INTERRUPT
    0.13
    Activations Density 0.274%

    No Known Activations