INDEX

Explanations

geographical location identifiers, specifically focusing on state and country names

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

iri

-0.16

aver

-0.15

ha

-0.15

á»ĩ

-0.15

ruc

-0.15

.Mode

-0.15

emat

-0.15

/tty

-0.15

zel

-0.14

aland

-0.14

POSITIVE LOGITS

Warnings

0.17

akedown

0.16

ene

0.15

etine

0.15

ĵĺ

0.15

pte

0.14

izzle

0.14

Reviewer

0.14

 Bien

0.14

KY

0.14

Activations Density 0.117%

geographical location identifiers, specifically focusing on state and country names

No Comments

No Known Activations