INDEX

Explanations

words that denote significance, intensity, or particularity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

estre

-0.18

Ð»Ð°ÑĤÐ¸

-0.16

ansson

-0.15

ust

-0.15

å«

-0.14

Bes

-0.14

 strncmp

-0.14

 whom

-0.13

zza

-0.13

iginal

-0.13

POSITIVE LOGITS

upo

0.17

lein

0.15

ly

0.15

sov

0.14

uably

0.14

 Credit

0.14

ÙĮ

0.14

çļĦæĺ¯

0.14

pecially

0.14

 evidence

0.13

Activations Density 0.119%

words that denote significance, intensity, or particularity in various contexts

No Comments

No Known Activations