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

    mentions of geographical locations and community-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oman
    -0.16
     exponent
    -0.15
    .nz
    -0.15
    amina
    -0.14
    eva
    -0.14
    è
    -0.14
    aub
    -0.14
     Neighborhood
    -0.14
    qing
    -0.14
     Campos
    -0.14
    POSITIVE LOGITS
     states
    0.28
     cities
    0.27
    states
    0.23
    -states
    0.23
     Midwest
    0.23
     Florida
    0.21
     States
    0.21
     estados
    0.20
    cities
    0.20
     Ohio
    0.20
    Activations Density 0.527%

    No Known Activations