Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 31450
    Prev
    Next
    INDEX
    Explanations

    instances and references to specific individuals or groups, particularly in contexts related to influence and actions in cultural or societal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    λει
    -0.16
    uce
    -0.15
    roke
    -0.15
    uis
    -0.15
    rray
    -0.15
    istrovstvÃŃ
    -0.14
    erge
    -0.14
    ogui
    -0.14
    XF
    -0.14
    ÑĥÑĢÑĥ
    -0.14
    POSITIVE LOGITS
    sein
    0.20
    iture
    0.17
    983
    0.14
     heure
    0.14
     etc
    0.14
    ANGUAGE
    0.14
     inn
    0.14
    USR
    0.14
     Wander
    0.14
    DateTime
    0.14
    Activations Density 0.136%

    No Known Activations