© 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. 26-LLAMASCOPE-RES-32K
    11. 10871
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minds
    -0.22
     Milton
    -0.18
     Manning
    -0.17
     Maul
    -0.16
    625
    -0.16
     Mund
    -0.15
     Mach
    -0.15
    apture
    -0.15
     Marilyn
    -0.15
    VML
    -0.15
    POSITIVE LOGITS
     message
    0.91
    message
    0.76
     messages
    0.75
     Message
    0.73
    -message
    0.70
    Message
    0.67
    _message
    0.66
     mess
    0.66
    .message
    0.66
     msg
    0.65
    Activations Density 0.220%

    No Known Activations