© 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. 29029
    Prev
    Next
    INDEX
    Explanations

    references to military actions or conflicts

    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
    onda
    -0.22
    ει
    -0.15
    yer
    -0.15
     Rein
    -0.15
    gles
    -0.14
    riad
    -0.14
     scal
    -0.14
    ymb
    -0.14
    abd
    -0.14
     пок
    -0.14
    POSITIVE LOGITS
    太éĥİ
    0.17
     CLAIM
    0.15
    ÃĸL
    0.15
    Ú©Ø´
    0.15
     Claims
    0.15
     claim
    0.15
     Equ
    0.15
     лак
    0.14
    zap
    0.14
    è
    0.14
    Activations Density 0.117%

    No Known Activations