© 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. 22-LLAMASCOPE-RES-32K
    6. 11079
    Prev
    Next
    INDEX
    Explanations

    elements related to cinematic disappointments and genre comparisons

    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
    endl
    -0.16
    olume
    -0.15
    ctest
    -0.14
    Jam
    -0.14
     Disaster
    -0.14
     bü
    -0.14
     tea
    -0.14
    .bulk
    -0.14
    undles
    -0.13
     Extr
    -0.13
    POSITIVE LOGITS
     noir
    0.30
     Noir
    0.28
     crime
    0.23
     pulp
    0.23
     Femme
    0.22
     femme
    0.21
     Crime
    0.20
    çĬ¯ç½ª
    0.19
     Violence
    0.19
     Neon
    0.19
    Activations Density 0.170%

    No Known Activations