INDEX

Explanations

references to success stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

umm

-0.17

 Resort

-0.15

 honeymoon

-0.14

Nam

-0.14

uber

-0.14

ibi

-0.13

ãĥ³ãĥĳ

-0.13

rello

-0.13

.scalablytyped

-0.13

POSITIVE LOGITS

aupt

0.15

 lumber

0.15

omez

0.15

kov

0.14

eras

0.14

 transcend

0.13

cairo

0.13

erde

0.13

Axe

0.13

 critics

0.13

Activations Density 0.000%

references to success stories

No Comments

No Known Activations