© 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. 16927
    Prev
    Next
    INDEX
    Explanations

    words indicating a sense of ability or capability, particularly in achieving or managing tasks

    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
    maktan
    -0.16
    mamak
    -0.16
    couz
    -0.15
    illard
    -0.15
    entionPolicy
    -0.15
    makta
    -0.15
    ÃŃg
    -0.15
    essen
    -0.15
    IIIK
    -0.15
    lius
    -0.15
    POSITIVE LOGITS
    able
    1.04
    ABLE
    0.72
    ables
    0.68
    ably
    0.67
    ability
    0.61
    ible
    0.61
    abel
    0.58
    ble
    0.56
    abled
    0.55
    abl
    0.55
    Activations Density 0.089%

    No Known Activations