© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    references to the word "it" and other pronouns that indicate subjectivity

    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
    rets
    -0.15
    iesen
    -0.14
     stood
    -0.14
    μή
    -0.14
    lect
    -0.14
     prevailed
    -0.13
    ÏĦιν
    -0.13
    ð
    -0.13
     exc
    -0.13
    ANC
    -0.13
    POSITIVE LOGITS
     turns
    0.20
    ching
    0.18
    chy
    0.17
     dawn
    0.16
     wa
    0.16
    .IsAny
    0.16
    asn
    0.15
    lan
    0.15
    pyx
    0.15
     OCC
    0.15
    Activations Density 0.115%

    No Known Activations