INDEX

Explanations

entities or terms related to specific categories or names

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

nek

-0.15

exact

-0.14

lander

-0.14

ÏħÎº

-0.14

once

-0.14

ials

-0.13

ussed

-0.13

hora

-0.13

reh

-0.13

ResponseStatus

-0.13

POSITIVE LOGITS

åŃĺäºİ

0.16

ÃĹ↵↵

0.15

aversable

0.14

ylvania

0.14

elight

0.14

Ã±ana

0.14

 kent

0.14

.Debugf

0.14

ildo

0.14

Activations Density 0.075%

entities or terms related to specific categories or names

No Comments

No Known Activations