INDEX

Explanations

references to significant rankings or milestones

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

oor

-0.16

abin

-0.14

isle

-0.14

gable

-0.14

obao

-0.14

ensible

-0.14

Det

-0.13

 Branch

-0.13

iskey

-0.13

otta

-0.13

POSITIVE LOGITS

igon

0.15

ald

0.15

HEET

0.14

swick

0.14

à¤¸à¤¨

0.14

(fi

0.14

æİĽ

0.13

éļĨ

0.13

orum

0.13

Activations Density 0.082%

references to significant rankings or milestones

No Comments

No Known Activations