© 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. 12-LLAMASCOPE-RES-32K
    6. 32413
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oth
    -0.14
    oret
    -0.14
    abel
    -0.14
    ailles
    -0.14
    ajs
    -0.13
    estre
    -0.13
    edis
    -0.13
    abet
    -0.13
    orer
    -0.13
     Chall
    -0.13
    POSITIVE LOGITS
    rido
    0.16
    erli
    0.16
    Sharper
    0.15
    inator
    0.15
    纳
    0.15
    .RGB
    0.14
    crest
    0.14
    credit
    0.14
    .www
    0.14
     tá»·
    0.13
    Activations Density 0.002%

    No Known Activations