© 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. 25-LLAMASCOPE-RES-32K
    11. 13312
    Prev
    Next
    INDEX
    Explanations

    words ending in "ent" or related suffixes indicating conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keit
    -0.20
    s
    -0.19
    र
    -0.17
    AllWindows
    -0.16
    bers
    -0.16
    heads
    -0.16
    ged
    -0.15
    arks
    -0.15
    Ùĩ
    -0.15
    pline
    -0.15
    POSITIVE LOGITS
    ertainment
    0.28
    ech
    0.26
    emente
    0.26
    ennial
    0.25
    ucky
    0.23
    eb
    0.22
    rop
    0.21
    ropy
    0.21
    wicklung
    0.21
    zia
    0.20
    Activations Density 0.129%

    No Known Activations