INDEX

Explanations

proper noun labels associated with various movies and entertainment content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ertz

-0.15

aversable

-0.15

ald

-0.15

UBL

-0.14

alach

-0.14

och

-0.14

 helicopt

-0.13

iple

-0.13

POSITIVE LOGITS

los

0.15

 drill

0.15

Kin

0.15

otas

0.14

iform

0.14

 Suff

0.14

rees

0.14

_configure

0.14

ores

0.14

olith

0.14

Activations Density 0.001%

proper noun labels associated with various movies and entertainment content

No Comments

No Known Activations