© 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. 25-LLAMASCOPE-RES-32K
    6. 17882
    Prev
    Next
    INDEX
    Explanations

    descriptions of condition and quality related to objects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voks
    -0.16
    _SAFE
    -0.15
    enus
    -0.15
    ots
    -0.15
     umb
    -0.14
    UMB
    -0.14
    _barrier
    -0.14
    оÑħ
    -0.14
    áž
    -0.14
    llen
    -0.13
    POSITIVE LOGITS
     shape
    0.77
     Shape
    0.64
    shape
    0.63
    Shape
    0.55
     condition
    0.51
     shapes
    0.49
    _shape
    0.48
    .shape
    0.47
    (shape
    0.43
     Shapes
    0.41
    Activations Density 0.046%

    No Known Activations