© 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. 1-LLAMASCOPE-RES-32K
    11. 6524
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "such" in various contexts

    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
    croft
    -0.18
    fty
    -0.16
    534
    -0.16
    yst
    -0.15
     Bik
    -0.15
    asher
    -0.14
    ropical
    -0.14
    Īĺ
    -0.14
    adge
    -0.14
    urgeon
    -0.14
    POSITIVE LOGITS
     cellForRowAt
    0.17
    esini
    0.14
    ething
    0.14
    udos
    0.14
    amps
    0.14
    enty
    0.13
    ahlen
    0.13
    ÙĪÙĤ
    0.13
    NamedQuery
    0.13
    hits
    0.13
    Activations Density 0.059%

    No Known Activations