© 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. 27-LLAMASCOPE-RES-32K
    6. 12067
    Prev
    Next
    INDEX
    Explanations

    terms related to the examination and classification of stars and celestial bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪIJäºĨ
    -0.17
    riba
    -0.16
    rees
    -0.16
    imli
    -0.16
    ultipart
    -0.15
    åĩºäºĨ
    -0.15
     erken
    -0.15
    uit
    -0.15
    china
    -0.15
    неÑģ
    -0.14
    POSITIVE LOGITS
    ieren
    0.26
    ählen
    0.25
    ndern
    0.25
    owaÄĩ
    0.22
    reiben
    0.22
    stellen
    0.20
     machen
    0.20
    ichern
    0.20
    uchen
    0.20
    auen
    0.19
    Activations Density 0.047%

    No Known Activations