© 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. 1-LLAMASCOPE-RES-32K
    6. 14612
    Prev
    Next
    INDEX
    Explanations

    references to the name "Salvador."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sgi
    -0.16
    ngo
    -0.16
    umph
    -0.15
    bnb
    -0.15
    thenReturn
    -0.15
    tra
    -0.14
    'http
    -0.14
    неÑģ
    -0.14
    ĽĦ
    -0.14
    778
    -0.14
    POSITIVE LOGITS
    .gdx
    0.18
    aso
    0.15
     substitutes
    0.15
    atom
    0.14
    ãĥ«ãĥķ
    0.14
    íĭ±
    0.14
    idth
    0.14
    ifier
    0.14
    _written
    0.13
    oll
    0.13
    Activations Density 0.001%

    No Known Activations