INDEX

Explanations

occurrences of the letter 'v'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

umno

-0.19

Ð¶Ð°

-0.16

_cv

-0.15

gen

-0.15

isen

-0.15

umper

-0.15

 interp

-0.15

 represented

-0.14

chten

-0.14

jerne

-0.14

POSITIVE LOGITS

oir

0.27

ingt

0.23

ende

0.20

rais

0.20

agues

0.19

Ã©n

0.19

rac

0.19

ierge

0.19

allon

0.18

ain

0.18

Activations Density 0.007%

occurrences of the letter 'v'

No Comments

No Known Activations