© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 30864
    Prev
    Next
    INDEX
    Explanations

    references to locations and geographical features

    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
     Southampton
    -0.20
     Tottenham
    -0.18
    UNCT
    -0.17
     Bronx
    -0.17
     Yorkshire
    -0.16
    NH
    -0.16
    Liverpool
    -0.15
     Glouce
    -0.15
     Buckingham
    -0.15
     Durham
    -0.15
    POSITIVE LOGITS
     Idaho
    0.71
     Boise
    0.65
     Nez
    0.40
     Spokane
    0.40
    Id
    0.39
     Ada
    0.39
     ID
    0.35
    IDA
    0.34
    (Id
    0.34
    ,ID
    0.33
    Activations Density 0.012%

    No Known Activations