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. 5-LLAMASCOPE-RES-32K
    6. 367
    Prev
    Next
    INDEX
    Explanations

    references to physical appearance or aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /scripts
    -0.17
    hai
    -0.17
    ha
    -0.17
    ácil
    -0.17
    x
    -0.16
    ib
    -0.15
     Pot
    -0.15
    age
    -0.15
    TEGER
    -0.15
     cur
    -0.15
    POSITIVE LOGITS
     Appearance
    0.20
     appearance
    0.19
    Appearance
    0.18
    #af
    0.17
    appearance
    0.17
    _FT
    0.16
    infeld
    0.15
    .ns
    0.15
    anje
    0.15
    æĢĸ
    0.15
    Activations Density 0.020%

    No Known Activations