INDEX

Explanations

mentions of Warner Bros

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

utton

-0.16

fern

-0.15

 regimes

-0.15

ory

-0.15

alten

-0.15

enders

-0.15

ä¸²

-0.15

lem

-0.14

ami

-0.14

 CALLBACK

-0.14

POSITIVE LOGITS

ouns

0.18

edImage

0.16

ment

0.15

lon

0.15

iddles

0.15

neau

0.15

lane

0.15

assing

0.14

exus

0.14

odic

0.14

Activations Density 0.012%

mentions of Warner Bros

No Comments

No Known Activations