© 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. 23-LLAMASCOPE-RES-32K
    11. 15301
    Prev
    Next
    INDEX
    Explanations

    concepts related to attraction and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.17
    dej
    -0.16
    ombine
    -0.15
    uien
    -0.15
    woff
    -0.15
    agini
    -0.15
    riba
    -0.14
    á»Ļt
    -0.14
    uler
    -0.14
    lossen
    -0.14
    POSITIVE LOGITS
     attracted
    0.64
     drawn
    0.64
     attraction
    0.53
     attracts
    0.45
     attract
    0.44
     Draw
    0.42
     grav
    0.41
    attr
    0.40
    draw
    0.40
     attractions
    0.40
    Activations Density 0.114%

    No Known Activations