© 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. 23-LLAMASCOPE-RES-32K
    11. 11379
    Prev
    Next
    INDEX
    Explanations

    references to taking control over one's own situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owitz
    -0.17
    806
    -0.17
    ihn
    -0.16
    ekim
    -0.16
    utz
    -0.15
     Coord
    -0.15
    odash
    -0.15
    htable
    -0.15
    azu
    -0.15
    åŁŁ
    -0.14
    POSITIVE LOGITS
     into
    0.28
     hands
    0.27
     nelle
    0.26
     in
    0.26
     Hands
    0.25
     Into
    0.25
     manos
    0.24
    èIJ½
    0.21
    Into
    0.21
    _into
    0.21
    Activations Density 0.069%

    No Known Activations