© 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. 26-LLAMASCOPE-RES-32K
    6. 6484
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sexuality and intimate relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shint
    -0.16
    ,↵
    -0.13
     getLogger
    -0.13
    arrison
    -0.13
    uffman
    -0.13
    emie
    -0.13
     Já
    -0.13
    ertura
    -0.12
    iedy
    -0.12
     Uncomment
    -0.12
    POSITIVE LOGITS
     \↵
    0.15
    ellen
    0.14
     gord
    0.13
    ocs
    0.13
    oca
    0.13
    éºĹ
    0.13
    ultiply
    0.13
     éĿ¢
    0.13
    antino
    0.13
     bump
    0.13
    Activations Density 0.015%

    No Known Activations