INDEX

Explanations

references to species and scientific classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eof

-0.16

ournals

-0.16

ames

-0.15

flo

-0.14

avan

-0.14

sian

-0.13

rika

-0.13

oke

-0.13

ç¹

-0.13

 ÐļÑĢÐ°ÑĹÐ½Ð°

-0.13

POSITIVE LOGITS

 Wikipedia

0.20

 wikipedia

0.17

 entry

0.16

-definition

0.15

 page

0.15

 official

0.14

avern

0.14

.htm

0.14

entry

0.14

Activations Density 0.099%

references to species and scientific classifications

No Comments

No Known Activations