INDEX

Explanations

references to legal cases or judicial proceedings

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

 rede

-0.15

ä¼į

-0.15

CTS

-0.15

oine

-0.15

ither

-0.14

ATUS

-0.14

atak

-0.13

/avatar

-0.13

arest

-0.13

lik

-0.13

POSITIVE LOGITS

'gc

0.14

 Ð²ÐµÐ»

0.14

rello

0.14

iev

0.14

vel

0.14

inja

0.13

kova

0.13

ulton

0.13

\modules

0.13

Activations Density 0.039%

references to legal cases or judicial proceedings

No Comments

No Known Activations