INDEX

Explanations

references to "forks" and variations of the word 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

egen

-0.17

ourd

-0.15

taj

-0.15

ury

-0.14

ence

-0.14

 offend

-0.14

ego

-0.13

ency

-0.13

 vast

-0.13

jee

-0.13

POSITIVE LOGITS

folio

0.19

bidden

0.18

ä½ľçĶ¨

0.17

ney

0.16

chan

0.16

onga

0.15

 NhÄ©

0.14

.nz

0.14

anden

0.14

ãĥ¬ãĤ¤

0.14

Activations Density 0.006%

references to "forks" and variations of the word in various contexts

No Comments

No Known Activations