© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 15655
    Prev
    Next
    INDEX
    Explanations

    negative prefixes and words associated with shortcomings or failures

    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
    atisation
    -0.20
    stration
    -0.20
    eration
    -0.18
    striction
    -0.18
    alysis
    -0.18
    anness
    -0.18
    igma
    -0.17
    iliation
    -0.17
    emption
    -0.17
    lessness
    -0.17
    POSITIVE LOGITS
    acious
    0.25
    urious
    0.25
    eworthy
    0.25
    arious
    0.24
    missive
    0.23
    itious
    0.22
    urous
    0.21
    ificent
    0.21
    lient
    0.20
    iguous
    0.20
    Activations Density 0.274%

    No Known Activations