INDEX

Explanations

references to specific dates 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ã¶t

-0.15

 Ø§ÙĦØ°

-0.15

 Leer

-0.15

Fot

-0.14

reu

-0.14

enge

-0.14

idar

-0.14

æ¨

-0.14

utto

-0.14

.datasets

-0.14

POSITIVE LOGITS

Weekly

0.18

 newspaper

0.18

weekly

0.17

 weekly

0.17

 Weekly

0.16

êµ°

0.15

è«ĸ

0.15

_issue

0.15

azzi

0.15

iss

0.15

Activations Density 0.014%

references to specific dates and publications

No Comments

No Known Activations