© 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. 16751
    Prev
    Next
    INDEX
    Explanations

    expressions indicating the highest quality or superiority

    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
    sembly
    -0.16
    Äĩi
    -0.15
    ÏĢÏĮ
    -0.14
    ilestone
    -0.14
    vt
    -0.14
    zens
    -0.14
    agua
    -0.14
    ponsive
    -0.14
    indle
    -0.14
    ssize
    -0.14
    POSITIVE LOGITS
    seller
    0.37
    -known
    0.36
    -selling
    0.35
    owing
    0.33
    -case
    0.32
    ow
    0.30
    est
    0.29
    -ever
    0.27
    ial
    0.27
    ows
    0.27
    Activations Density 0.073%

    No Known Activations