INDEX

Explanations

geographical locations and proper nouns related to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

obus

-0.15

odate

-0.14

toDate

-0.14

idar

-0.14

plode

-0.14

-0.13

ance

-0.13

 Derm

-0.13

izona

-0.13

ialog

-0.13

POSITIVE LOGITS

.cloudflare

0.16

SV

0.15

.languages

0.15

GDK

0.15

ê²½

0.14

/tiny

0.14

Sey

0.14

Ã¼c

0.14

DBObject

0.13

Activations Density 0.007%

geographical locations and proper nouns related to places

No Comments

No Known Activations