© 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. 30-LLAMASCOPE-RES-32K
    11. 17427
    Prev
    Next
    INDEX
    Explanations

    key nouns and certain prefixes or suffixes that indicate specific categories or attributes

    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
    ocos
    -0.21
    èĤ²
    -0.19
     nÄĥ
    -0.19
     Gram
    -0.17
    aign
    -0.15
    andelier
    -0.15
     gram
    -0.15
    ousel
    -0.15
    Gram
    -0.15
    zend
    -0.15
    POSITIVE LOGITS
     ta
    0.20
    ta
    0.18
    Ta
    0.18
     Conc
    0.18
     Ta
    0.17
     Archer
    0.17
     Tanner
    0.16
     Shortcut
    0.16
     conc
    0.15
    -Ta
    0.15
    Activations Density 0.019%

    No Known Activations