INDEX

Explanations

occurrences of the word "publish" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.19

arrow

-0.15

 Acres

-0.15

ad

-0.15

red

-0.15

Ã«

-0.15

ides

-0.15

 palp

-0.14

ang

-0.14

POSITIVE LOGITS

(crate

0.18

iego

0.16

typeid

0.16

íĮĲ

0.15

AndGet

0.14

iative

0.14

skirts

0.14

rrha

0.14

TypeDef

0.14

itive

0.14

Activations Density 0.059%

occurrences of the word "publish" and its variations

No Comments

No Known Activations