INDEX

Explanations

proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

err

-0.16

YLE

-0.15

 Truck

-0.15

ÑĢÐ¾Ñĩ

-0.15

 embed

-0.15

inki

-0.14

 Cumberland

-0.14

 kindness

-0.14

err

-0.14

inf

-0.14

POSITIVE LOGITS

lar

0.21

Ã½n

0.19

anca

0.19

erli

0.18

aca

0.18

irma

0.17

LAR

0.16

ãĥ³ãĥĩ

0.16

acl

0.16

Ã½t

0.16

Activations Density 0.007%

proper nouns, particularly names and locations

No Comments

No Known Activations