© 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. 22-LLAMASCOPE-RES-32K
    11. 16525
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vro
    -0.18
    ãĥ³ãĥĢ
    -0.17
    argent
    -0.16
    jeme
    -0.15
    AccessException
    -0.14
    upro
    -0.14
    Ä±ÅŁma
    -0.14
    legg
    -0.14
    iglia
    -0.14
    cplusplus
    -0.14
    POSITIVE LOGITS
     sounds
    1.05
     Sounds
    0.96
    Sounds
    0.93
    sounds
    0.93
     sound
    0.92
     sounded
    0.83
     sounding
    0.80
     Sound
    0.78
    sound
    0.77
    Sound
    0.75
    Activations Density 0.221%

    No Known Activations