INDEX

Explanations

instances of the word "these" and variations of "these" used 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tring

-0.18

ve

-0.18

veau

-0.17

ÄŁa

-0.16

shit

-0.16

sss

-0.15

leans

-0.15

ss

-0.14

recated

-0.14

POSITIVE LOGITS

curity

0.21

quence

0.21

è²¬

0.16

 meisten

0.16

è´£

0.15

cond

0.15

quential

0.14

idl

0.14

VT

0.14

alice

0.14

Activations Density 0.082%

instances of the word "these" and variations of "these" used in various contexts

No Comments

No Known Activations