INDEX

Explanations

phrases related to location and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ument

-0.16

subst

-0.16

rooms

-0.15

paces

-0.15

Ð±Ð¾ÑĢ

-0.14

ocaust

-0.14

 Anita

-0.14

 credit

-0.14

INV

-0.13

ãĥ¼ãĤ¸

-0.13

POSITIVE LOGITS

 Sector

0.15

etti

0.15

Ø±ÙĪØ³

0.14

utto

0.14

alic

0.14

asset

0.14

ToBounds

0.13

ãĥ¼ãĥĦ

0.13

ayacak

0.13

ascript

0.13

Activations Density 0.063%

phrases related to location and accessibility

No Comments

No Known Activations