INDEX

Explanations

references to significant entities or concepts related to community and social structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

sit

-0.15

-0.14

esel

-0.14

jem

-0.14

eman

-0.14

deme

-0.14

ÑĨÐ¸Ð¿

-0.14

ries

-0.14

RIES

-0.14

-0.13

POSITIVE LOGITS

cht

0.15

[assembly

0.14

 OnDestroy

0.14

AFE

0.14

UNET

0.13

Å¼e

0.13

 OMIT

0.13

vore

0.13

 interchangeable

0.13

kip

0.13

Activations Density 0.098%

references to significant entities or concepts related to community and social structure

No Comments

No Known Activations