INDEX

Explanations

references to specific instances or points of details in discussions or texts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 McGu

-0.15

ohl

-0.14

ibbon

-0.14

 Rockefeller

-0.14

 Roths

-0.14

 underlying

-0.14

ableObject

-0.14

eer

-0.14

onio

-0.14

eyed

-0.14

POSITIVE LOGITS

deo

0.17

_refl

0.17

dev

0.15

MethodImpl

0.15

ricia

0.14

 dialogs

0.14

uars

0.14

uu

0.14

 Flames

0.14

uw

0.14

Activations Density 0.939%

references to specific instances or points of details in discussions or texts

No Comments

No Known Activations