INDEX

Explanations

questions relating to timing or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

rest

-0.15

isson

-0.15

lix

-0.15

Disposition

-0.15

ÄħÅ¼

-0.14

.echo

-0.14

eos

-0.14

stadt

-0.14

illac

-0.14

tran

-0.13

POSITIVE LOGITS

ienes

0.17

Î½Î¹

0.16

amat

0.15

 rá»Ŀi

0.14

ORTH

0.14

opard

0.14

roit

0.14

ahr

0.14

utherford

0.13

Activations Density 0.039%

questions relating to timing or occurrences

No Comments

No Known Activations