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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1671
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the allocation or prioritization of importance or value

    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
    zeug
    -0.16
    opup
    -0.15
    trag
    -0.15
    /from
    -0.15
     Avec
    -0.15
    ecz
    -0.15
    ape
    -0.14
    illy
    -0.14
    atsu
    -0.14
     apply
    -0.14
    POSITIVE LOGITS
     emphasis
    0.30
     bets
    0.29
     importance
    0.23
     blame
    0.23
    emphasis
    0.23
     Importance
    0.21
     emphasize
    0.19
     demands
    0.19
     placed
    0.18
     Limits
    0.18
    Activations Density 0.044%

    No Known Activations