© 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. 17-LLAMASCOPE-RES-32K
    6. 22578
    Prev
    Next
    INDEX
    Explanations

    details related to accidents and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    оÑĢаз
    -0.17
    poz
    -0.15
    ueur
    -0.14
    åĽ´
    -0.14
    unkt
    -0.14
    antine
    -0.13
     storms
    -0.13
    ilit
    -0.13
    ÑĢина
    -0.13
     NTN
    -0.13
    POSITIVE LOGITS
     damage
    0.35
    damage
    0.31
     Damage
    0.30
     injuries
    0.28
    Damage
    0.28
     DAMAGE
    0.28
     damages
    0.26
     injury
    0.25
     damaged
    0.23
    .damage
    0.23
    Activations Density 0.182%

    No Known Activations