© 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. 20-LLAMASCOPE-RES-32K
    11. 21673
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to various entities and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦and
    -0.15
    âĢ¦I
    -0.15
    âĢ¦it
    -0.15
    âĢ¦but
    -0.15
    âĢ¦↵↵
    -0.15
    âĢ¦↵
    -0.15
    ostringstream
    -0.14
    âĢ¦the
    -0.14
     âĢ¦↵
    -0.13
    âĢ¦↵↵↵
    -0.13
    POSITIVE LOGITS
     erotik
    0.15
     addCriterion
    0.15
     omas
    0.13
     seksi
    0.13
    IBUTE
    0.13
    ERICA
    0.13
    AMERA
    0.12
     provoz
    0.12
    ÐķС
    0.12
     kabil
    0.12
    Activations Density 1.524%

    No Known Activations