© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 28227
    Prev
    Next
    INDEX
    Explanations

    references to media content, particularly related to educational and social themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dden
    -0.15
     otherwise
    -0.14
     revis
    -0.14
    ounder
    -0.14
    ountains
    -0.14
     visita
    -0.13
    uro
    -0.13
     gsi
    -0.13
    ÅĤem
    -0.13
     spot
    -0.13
    POSITIVE LOGITS
    ıi
    0.15
    arden
    0.15
    çĶ·åŃIJ
    0.14
    amoto
    0.14
    wick
    0.14
    VENTORY
    0.14
    Ļ
    0.14
    ctp
    0.14
    iyel
    0.14
    .ErrorCode
    0.13
    Activations Density 2.044%

    No Known Activations