© 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. 9-LLAMASCOPE-RES-32K
    11. 27377
    Prev
    Next
    INDEX
    Explanations

    the main characters in various narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reau
    -0.18
    .opendaylight
    -0.15
    rir
    -0.14
     Vital
    -0.13
    arranty
    -0.13
    ãĥŃãĥ³
    -0.13
    ARRIER
    -0.13
    eldorf
    -0.13
    submenu
    -0.13
    ãĥĨãĥ«
    -0.13
    POSITIVE LOGITS
    ç£
    0.15
    lsen
    0.14
    andas
    0.13
    iverse
    0.13
     banda
    0.13
     bilm
    0.13
    ichten
    0.13
     recourse
    0.13
    raction
    0.12
    ois
    0.12
    Activations Density 0.170%

    No Known Activations