© 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. 30-LLAMASCOPE-RES-32K
    11. 16776
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons and justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /respond
    -0.20
    rub
    -0.18
    NotFoundError
    -0.17
    ÙģÙĤ
    -0.16
     Rabbit
    -0.15
     rubber
    -0.15
    rabbit
    -0.15
    997
    -0.14
     Replies
    -0.14
    .EVT
    -0.14
    POSITIVE LOGITS
     reason
    0.67
     reasons
    0.65
    reason
    0.53
     Reasons
    0.47
    Reason
    0.46
     Reason
    0.44
    .reason
    0.43
    _reason
    0.41
    åİŁåĽł
    0.39
    çIJĨçĶ±
    0.36
    Activations Density 0.095%

    No Known Activations