Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 6185
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly related to men

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.20
    tica
    -0.19
    eriod
    -0.18
    engin
    -0.18
    erif
    -0.17
    erin
    -0.16
    dete
    -0.16
    erde
    -0.16
    ted
    -0.16
    agini
    -0.15
    POSITIVE LOGITS
    folk
    0.49
    opause
    0.46
    aces
    0.38
    ial
    0.38
    ager
    0.35
    aced
    0.34
    ials
    0.33
    /w
    0.33
    's
    0.31
    fol
    0.30
    Activations Density 0.034%

    No Known Activations