INDEX

Explanations

code-related elements and references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

isque

-0.17

 Latter

-0.15

.bz

-0.14

yal

-0.14

 penny

-0.14

mun

-0.14

RenderTarget

-0.13

Äĩi

-0.13

alborg

-0.13

ÙĬØ§ÙĨ

-0.13

POSITIVE LOGITS

Ð¾Ð±Ñĭ

0.16

croft

0.15

0.14

rec

0.14

opies

0.14

ãĤ¤ãĤº

0.14

qid

0.14

agram

0.14

ough

0.14

Activations Density 0.733%

code-related elements and references

No Comments

No Known Activations