© 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. 26-LLAMASCOPE-RES-32K
    11. 5625
    Prev
    Next
    INDEX
    Explanations

    specific terms and names associated with organizational or scientific methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elman
    -0.19
    zan
    -0.15
    /topics
    -0.15
    sock
    -0.15
    ecies
    -0.14
     pap
    -0.14
     Bet
    -0.14
    lename
    -0.14
     Blanch
    -0.14
     Pale
    -0.14
    POSITIVE LOGITS
    reff
    0.16
    bac
    0.15
    andi
    0.15
    ALT
    0.15
    IRE
    0.15
    alt
    0.15
    angel
    0.15
    UNET
    0.15
     toArray
    0.15
    RS
    0.15
    Activations Density 0.030%

    No Known Activations