INDEX

Explanations

proper nouns associated with places, institutions, or specific demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ipers

-0.15

Eg

-0.15

hood

-0.14

 Beard

-0.14

UFFIX

-0.14

artment

-0.14

 Tout

-0.14

 Dove

-0.13

stants

-0.13

POSITIVE LOGITS

ilter

0.16

/*@

0.15

Feat

0.14

unpack

0.14

enu

0.14

ileo

0.14

.writeValue

0.13

iams

0.13

 FileAccess

0.13

Î¹Ïİ

0.13

Activations Density 0.004%

proper nouns associated with places, institutions, or specific demographics

No Comments

No Known Activations