© 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. 30-LLAMASCOPE-RES-32K
    6. 24685
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding the evaluation and assessment of effectiveness, validity, and authority related to various subjects

    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
    immel
    -0.15
    orne
    -0.14
    rof
    -0.14
    zcze
    -0.14
    ãĥ³ãĤ°
    -0.13
    asurable
    -0.13
     jim
    -0.13
    ãĥ³ãĤ¯
    -0.13
    240
    -0.13
    levant
    -0.13
    POSITIVE LOGITS
     appropri
    0.44
     adequ
    0.36
     worth
    0.36
     efficacy
    0.35
     validity
    0.34
     effectiveness
    0.34
     whether
    0.34
     suitability
    0.34
     viability
    0.34
     suff
    0.33
    Activations Density 0.449%

    No Known Activations