INDEX

Explanations

references to measurements, statistics, and general data indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

aque

-0.17

ades

-0.15

 Muss

-0.15

strand

-0.15

dbl

-0.14

acas

-0.14

lander

-0.14

WW

-0.14

 poss

-0.14

 Howell

-0.14

POSITIVE LOGITS

alion

0.15

ÑĢÐ°Ð±

0.14

/stat

0.14

etri

0.14

ALLOC

0.13

.GetInstance

0.13

_flip

0.13

hong

0.13

alie

0.13

glich

0.13

Activations Density 0.041%

references to measurements, statistics, and general data indicators

No Comments

No Known Activations