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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 7328
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "in" and to a lesser extent, contexts related to specific subjects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oba
    -0.20
    ité
    -0.15
    idUser
    -0.14
    abay
    -0.14
    abar
    -0.14
    rá
    -0.13
    hill
    -0.13
    اÙĨÛĮ
    -0.13
    nemonic
    -0.13
    anker
    -0.13
    POSITIVE LOGITS
    ampo
    0.18
    ç¢
    0.17
    ipay
    0.14
    atz
    0.14
    sel
    0.14
    dech
    0.13
    amm
    0.13
    jected
    0.13
    Reviewed
    0.13
    lint
    0.13
    Activations Density 0.114%

    No Known Activations