Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 31045
    Prev
    Next
    INDEX
    Explanations

    descriptors of competence and skill

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.17
    ekim
    -0.16
    ucked
    -0.16
    oba
    -0.16
    еÑģÑı
    -0.16
    å¦
    -0.16
    ucken
    -0.15
    iverz
    -0.15
    imity
    -0.15
    kaar
    -0.15
    POSITIVE LOGITS
    ally
    0.16
    inent
    0.15
    abal
    0.15
    yat
    0.14
    empt
    0.14
     camps
    0.14
     dimensional
    0.14
    627
    0.14
    sted
    0.14
    toPromise
    0.14
    Activations Density 0.050%

    No Known Activations