INDEX

Explanations

key phrases related to formal declarations or statements

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

imd

-0.17

ghan

-0.17

iki

-0.15

cala

-0.15

isty

-0.15

ADATA

-0.14

assage

-0.14

oul

-0.14

Kov

-0.14

)const

-0.14

POSITIVE LOGITS

 rehab

0.20

 rehabilitation

0.17

 Gors

0.16

izu

0.15

 Sunder

0.14

 tane

0.14

rel

0.14

cul

0.14

 sabot

0.14

 Rehab

0.14

Activations Density 0.000%

key phrases related to formal declarations or statements

No Comments

No Known Activations