© 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. 7-LLAMASCOPE-RES-32K
    11. 19970
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedures and system functionality in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylon
    -0.16
    ryn
    -0.16
    ÑĻ
    -0.14
    osen
    -0.14
    loud
    -0.14
    ucci
    -0.14
    .Usage
    -0.13
    aty
    -0.13
    ngo
    -0.13
    vale
    -0.13
    POSITIVE LOGITS
     Strand
    0.18
    arsi
    0.17
    667
    0.17
    زا
    0.15
    595
    0.15
    ADF
    0.15
    orny
    0.15
    oa
    0.14
     Sym
    0.14
    Äħ
    0.14
    Activations Density 0.296%

    No Known Activations