© 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. 6478
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to counts and quantities

    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
    ese
    -0.16
    glich
    -0.15
    leting
    -0.15
    맥
    -0.14
    gov
    -0.14
    ady
    -0.14
    gard
    -0.14
    OTE
    -0.14
    391
    -0.14
    že
    -0.14
    POSITIVE LOGITS
    ayscale
    0.18
     whe
    0.17
    klad
    0.17
    ojÃŃ
    0.16
     Wheeler
    0.15
    /single
    0.15
     ingredient
    0.14
     tiers
    0.14
    ingredient
    0.14
    nof
    0.14
    Activations Density 0.101%

    No Known Activations