INDEX

Explanations

references to specific entities, actions, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

enko

-0.15

yu

-0.15

andex

-0.14

warz

-0.14

 steep

-0.14

uyen

-0.13

anked

-0.13

elic

-0.13

ÅĤo

-0.13

rending

-0.13

POSITIVE LOGITS

ocup

0.15

ÃŃc

0.15

CLU

0.14

acam

0.14

.Helper

0.14

 Dove

0.14

-Identifier

0.14

ãģĭãģĹ

0.14

ices

0.14

Bars

0.13

Activations Density 0.633%

references to specific entities, actions, or conditions

No Comments

No Known Activations