© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 31905
    Prev
    Next
    INDEX
    Explanations

    terms related to keyword research and SEO strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĺħ
    -0.14
    IBUTE
    -0.14
    qml
    -0.13
    ç½²
    -0.13
     Governance
    -0.13
    ä¸ĺ
    -0.13
     Consent
    -0.13
    akedown
    -0.13
    fax
    -0.13
    abor
    -0.13
    POSITIVE LOGITS
     Keyword
    0.33
     keyword
    0.33
     keywords
    0.31
     competitive
    0.30
     phrases
    0.29
     Keywords
    0.29
     competition
    0.29
     Phrase
    0.29
     phrase
    0.29
     competitor
    0.29
    Activations Density 0.051%

    No Known Activations