© 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. 6-LLAMASCOPE-RES-32K
    11. 10213
    Prev
    Next
    INDEX
    Explanations

    the use of parentheses and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enu
    -0.17
     eyed
    -0.15
    ncy
    -0.15
    ourt
    -0.15
    upro
    -0.14
    ency
    -0.14
    upal
    -0.14
     ÙĦغ
    -0.14
    úp
    -0.14
    orney
    -0.14
    POSITIVE LOGITS
    ,nil
    0.16
     sol
    0.15
     Cain
    0.15
    roads
    0.14
    ìĿij
    0.14
    col
    0.14
    å¿Ĺ
    0.14
    ROUT
    0.13
    ziel
    0.13
    Ĥ¬
    0.13
    Activations Density 0.020%

    No Known Activations