© 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. 6-LLAMASCOPE-RES-32K
    11. 7960
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Russian
    -0.16
    /read
    -0.15
    awah
    -0.15
     ramifications
    -0.15
     rigorous
    -0.15
    ight
    -0.15
     routine
    -0.15
    ights
    -0.15
    liers
    -0.14
    Body
    -0.14
    POSITIVE LOGITS
    efined
    0.24
    asmus
    0.20
    ourke
    0.20
    ansom
    0.18
    cliffe
    0.18
    entrant
    0.17
    nant
    0.17
    aldo
    0.16
    uffles
    0.16
    naissance
    0.16
    Activations Density 1.405%

    No Known Activations