INDEX

Explanations

locations and entities related to specific events or contexts

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

UD

-0.16

åĲ§

-0.15

Gee

-0.14

 Fold

-0.14

Breadcrumb

-0.14

\<

-0.14

Eventually

-0.13

Dud

-0.13

ud

-0.13

tit

-0.13

POSITIVE LOGITS

0.17

0.16

 GOODMAN

0.14

isz

0.14

cos

0.14

say

0.14

issant

0.14

 stran

0.14

dog

0.14

strained

0.14

Activations Density 0.175%

locations and entities related to specific events or contexts

No Comments

No Known Activations