INDEX

Explanations

references to specific variables or objects in code or programming contexts

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ire

-0.15

 kÃª

-0.15

éĢģæĸĻçĦ¡æĸĻ

-0.15

qli

-0.14

 addCriterion

-0.14

wnd

-0.14

tu

-0.14

-pdf

-0.13

eras

-0.13

POSITIVE LOGITS

st

0.14

aybe

0.14

UT

0.14

utos

0.14

 otherwise

0.13

á»©a

0.13

 precisely

0.13

fr

0.13

errs

0.13

err

0.13

Activations Density 0.483%

references to specific variables or objects in code or programming contexts

No Comments

No Known Activations