INDEX

Explanations

references to arrests and legal actions related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ius

-0.14

hta

-0.14

 Experience

-0.14

YNC

-0.14

 Dahl

-0.14

bu

-0.13

iske

-0.13

 Flowers

-0.13

 riders

-0.13

illas

-0.13

POSITIVE LOGITS

Perm

0.16

unken

0.15

zure

0.15

astery

0.14

lÃ¤

0.14

ument

0.14

uve

0.14

cter

0.13

 ragaz

0.13

ominated

0.13

Activations Density 0.136%

references to arrests and legal actions related to individuals

No Comments

No Known Activations