INDEX

Explanations

technical elements or tags in code or markup

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

asant

-0.16

utter

-0.15

Moy

-0.15

rieg

-0.15

lando

-0.14

 Ð¿Ð°

-0.14

Zy

-0.14

whe

-0.14

azers

-0.14

POSITIVE LOGITS

edor

0.16

kate

0.15

onga

0.14

isen

0.14

elop

0.13

 Conc

0.13

acco

0.13

ROP

0.13

ivi

0.13

ONGO

0.13

Activations Density 0.001%

technical elements or tags in code or markup

No Comments

No Known Activations