INDEX

Explanations

instances of the word "into."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÙĪÙĨØ¯

-0.16

re

-0.15

oko

-0.15

ê³Ħ

-0.15

rej

-0.15

kre

-0.14

 Reese

-0.14

Ard

-0.14

rogram

-0.14

=re

-0.14

POSITIVE LOGITS

estar

0.16

lingen

0.16

illon

0.14

ivet

0.14

proxy

0.14

vel

0.14

åĩºåĵģ

0.14

lify

0.14

ä¸įè¿ĩ

0.14

Fant

0.14

Activations Density 0.015%

instances of the word "into."

No Comments

No Known Activations