INDEX

Explanations

the occurrence of the word "Tor" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

izi

-0.16

irs

-0.14

OrFail

-0.14

enus

-0.14

InputElement

-0.14

kÃ¼

-0.14

ymes

-0.14

é¢ĺ

-0.14

arend

-0.13

otherwise

-0.13

POSITIVE LOGITS

mented

0.28

rance

0.24

adol

0.21

oidal

0.21

rens

0.20

onto

0.19

reon

0.19

ment

0.19

rence

0.19

ments

0.18

Activations Density 0.009%

the occurrence of the word "Tor" in various contexts

No Comments

No Known Activations