© 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. 24-LLAMASCOPE-RES-32K
    11. 6178
    Prev
    Next
    INDEX
    Explanations

    negative or low-quality aspects of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogr
    -0.16
    éIJ
    -0.15
    alta
    -0.14
    бо
    -0.14
    ÑĤÑĥÑĢа
    -0.13
    own
    -0.13
    IfNeeded
    -0.13
    aldo
    -0.12
    ãĤ¢ãĥ³
    -0.12
    dong
    -0.12
    POSITIVE LOGITS
     to
    0.78
     να
    0.43
    to
    0.41
    	to
    0.39
    _to
    0.37
     zu
    0.35
     Äijá»ĥ
    0.33
    ãĤĴ
    0.31
    ToUpdate
    0.31
     ÑĩÑĤобÑĭ
    0.31
    Activations Density 0.322%

    No Known Activations