© 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. 31-LLAMASCOPE-RES-32K
    11. 5836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating geographic locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakne
    -0.18
     Og
    -0.17
     fractional
    -0.17
    ettle
    -0.16
    eshire
    -0.16
    taire
    -0.15
    ÄĻk
    -0.15
     prostituerte
    -0.15
    Utf
    -0.15
    illard
    -0.15
    POSITIVE LOGITS
     de
    0.25
     en
    0.25
     det
    0.24
     et
    0.23
     sit
    0.23
     den
    0.23
     sagen
    0.20
     sin
    0.20
    bage
    0.19
     dette
    0.19
    Activations Density 0.034%

    No Known Activations