INDEX

Explanations

references to journalistic entities or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

vp

-0.15

ampa

-0.15

ober

-0.15

ugas

-0.14

 Myers

-0.14

hurst

-0.14

usc

-0.13

orpor

-0.13

orca

-0.13

 Bristol

-0.13

POSITIVE LOGITS

 verm

0.16

hausen

0.15

edic

0.15

omba

0.15

itzer

0.15

otive

0.15

oui

0.14

_AVAILABLE

0.14

 Olympia

0.14

ÃŃv

0.14

Activations Density 0.038%

references to journalistic entities or sources

No Comments

No Known Activations