INDEX

Explanations

references to roles, positions, or individuals related to content creation and editing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

endir

-0.16

arend

-0.15

Î¿Îº

-0.14

unga

-0.14

_USAGE

-0.14

alo

-0.14

 Gingrich

-0.14

ä»ĺãģĳ

-0.14

.persistent

-0.14

alan

-0.14

POSITIVE LOGITS

 Pack

0.18

PACK

0.18

Pack

0.17

 Pref

0.16

 PACK

0.16

Popover

0.15

rig

0.15

 pack

0.15

gere

0.14

acey

0.14

Activations Density 0.001%

references to roles, positions, or individuals related to content creation and editing

No Comments

No Known Activations