© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 22900
    Prev
    Next
    INDEX
    Explanations

    key terms related to consumer trends and product categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ime
    -0.18
    riad
    -0.18
     tense
    -0.17
    ype
    -0.17
    oggle
    -0.16
    odos
    -0.16
    patch
    -0.16
    ube
    -0.16
    wy
    -0.16
    imer
    -0.15
    POSITIVE LOGITS
    entieth
    0.21
    ãģĬãĤĬ
    0.19
     nhiên
    0.19
    ÑĩаÑģ
    0.19
    =T
    0.19
    othy
    0.18
    bearer
    0.17
    yc
    0.17
    phoon
    0.16
    esseract
    0.16
    Activations Density 1.089%

    No Known Activations