© 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. 15-LLAMASCOPE-RES-32K
    11. 5823
    Prev
    Next
    INDEX
    Explanations

    terms related to creative expression and individuality in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лев
    -0.13
    xies
    -0.12
    нев
    -0.12
    вен
    -0.12
    âĢ¦↵↵↵
    -0.12
    lien
    -0.12
     [âĢ¦]
    -0.11
     [âĢ¦
    -0.11
    antz
    -0.11
    amedi
    -0.11
    POSITIVE LOGITS
    ãĥ³ãĥĩ
    0.13
    ìłĿ
    0.13
    .au
    0.13
    ioned
    0.13
    redients
    0.13
    (#)
    0.12
    /OR
    0.12
    ëŁ
    0.12
    ">//
    0.12
    ivos
    0.12
    Activations Density 4.393%

    No Known Activations