© 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. 12-LLAMASCOPE-RES-32K
    11. 31750
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicative of recommendations or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ackers
    -0.16
    ucha
    -0.16
    arus
    -0.16
    ilde
    -0.15
    ulings
    -0.15
    ichael
    -0.15
    quist
    -0.14
    edeki
    -0.14
    ighton
    -0.14
    ardo
    -0.14
    POSITIVE LOGITS
    ively
    0.23
    ìĤ¬íķŃ
    0.17
     ìĤ¬íķŃ
    0.16
    ëģĶ
    0.16
    entially
    0.16
     ìĭ¶
    0.16
    IVE
    0.15
    iments
    0.15
    ive
    0.15
    oo
    0.15
    Activations Density 0.049%

    No Known Activations