INDEX

Explanations

instances of the letter "S" 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

aga

-0.20

igner

-0.19

pur

-0.17

cheng

-0.16

DL

-0.16

ci

-0.16

Ð¿

-0.16

ell

-0.16

ubs

-0.16

alt

-0.15

POSITIVE LOGITS

vet

0.23

ven

0.20

oren

0.20

edef

0.19

ond

0.19

rin

0.18

ianne

0.18

zym

0.18

reten

0.17

ergy

0.17

Activations Density 0.033%

instances of the letter "S" in various contexts

No Comments

No Known Activations