© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 30431
    Prev
    Next
    INDEX
    Explanations

    mentions of groups, communities, or collectives involving people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -animate
    -0.15
     cons
    -0.15
    andest
    -0.14
    enou
    -0.14
    ppo
    -0.14
    /ec
    -0.14
    iani
    -0.14
    еко
    -0.14
    irst
    -0.13
     pump
    -0.13
    POSITIVE LOGITS
    RITE
    0.19
    lak
    0.17
    aux
    0.16
    tere
    0.16
    ball
    0.15
    both
    0.15
    ussels
    0.15
     Ludwig
    0.15
     Both
    0.14
    ele
    0.14
    Activations Density 0.389%

    No Known Activations