© 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. 4-LLAMASCOPE-RES-32K
    11. 25454
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to summation in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     du
    -0.17
    fty
    -0.16
    ICI
    -0.15
    ling
    -0.15
    lap
    -0.15
     Exp
    -0.14
    ching
    -0.14
    zos
    -0.14
    lename
    -0.14
    uming
    -0.14
    POSITIVE LOGITS
     saliva
    0.15
    Ñıж
    0.15
    berger
    0.15
    ofs
    0.15
     Tol
    0.14
    atik
    0.14
    .qual
    0.14
    /Edit
    0.14
    riot
    0.14
    |R
    0.13
    Activations Density 0.046%

    No Known Activations