© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and classification criteria in a professional or formal context

    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
    ieces
    -0.15
    екÑĤÑĥ
    -0.15
    _FOCUS
    -0.14
    SEG
    -0.14
    ÑĢеменно
    -0.14
    ool
    -0.14
    thren
    -0.14
    oders
    -0.14
    Flash
    -0.14
    _MO
    -0.14
    POSITIVE LOGITS
    ML
    0.21
    ml
    0.20
    _diag
    0.18
     Ser
    0.18
     ML
    0.17
     MLA
    0.17
     diary
    0.17
     Grave
    0.17
     gravity
    0.16
    diag
    0.16
    Activations Density 0.040%

    No Known Activations