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. 27-LLAMASCOPE-RES-32K
    6. 1735
    Prev
    Next
    INDEX
    Explanations

    key punctuation marks and certain phrases that indicate dialogue or reporting of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponge
    -0.17
    avel
    -0.14
     Nature
    -0.13
    ãĥ«ãĥķ
    -0.13
    pong
    -0.13
    cul
    -0.13
    Bezier
    -0.13
    aru
    -0.13
     Eisenhower
    -0.13
    ads
    -0.13
    POSITIVE LOGITS
    etheless
    0.16
    IOS
    0.15
    ucz
    0.15
    Ч
    0.14
    _audit
    0.14
    amber
    0.14
    ique
    0.13
     Vivo
    0.13
    ám
    0.13
    eos
    0.13
    Activations Density 0.019%

    No Known Activations