INDEX

Explanations

expressions confirming the correctness or standards of technical language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rum

-0.15

iane

-0.14

irma

-0.14

Themes

-0.14

 Themes

-0.14

 particular

-0.13

Tele

-0.13

 Ders

-0.13

ben

-0.13

ross

-0.13

POSITIVE LOGITS

jian

0.16

MC

0.15

åļ

0.15

Å¾ÃŃ

0.15

vro

0.15

 Strict

0.15

itr

0.14

loop

0.14

Strict

0.14

ÙĨØ¯

0.14

Activations Density 0.141%

expressions confirming the correctness or standards of technical language

No Comments

No Known Activations