© 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. 18-LLAMASCOPE-RES-32K
    11. 24838
    Prev
    Next
    INDEX
    Explanations

    key concepts and questions related to atheism and existential beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elu
    -0.16
    plusplus
    -0.15
    igid
    -0.14
    ISCO
    -0.14
     Babylon
    -0.14
     Bey
    -0.14
    podob
    -0.14
     sprav
    -0.14
    lesai
    -0.14
    ssp
    -0.13
    POSITIVE LOGITS
    wyn
    0.17
     Epic
    0.15
     bite
    0.15
     Daw
    0.15
    borough
    0.15
    ائÙĬØ©
    0.15
     Evidence
    0.14
    COPE
    0.14
     Masc
    0.14
     atheists
    0.14
    Activations Density 0.087%

    No Known Activations