INDEX

Explanations

terms related to publishing and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ang

-0.15

Ã«

-0.15

arrow

-0.15

ad

-0.15

ed

-0.15

 palp

-0.14

Ú¯Ø§Ùĩ

-0.14

leon

-0.14

etter

-0.14

POSITIVE LOGITS

(crate

0.19

isz

0.16

ulumi

0.15

lou

0.15

/export

0.15

ICATION

0.15

typeid

0.14

skirts

0.14

iego

0.14

 escorte

0.14

Activations Density 0.058%

terms related to publishing and publications

No Comments

No Known Activations

terms related to publishing and publications

No Comments

No Known Activations