INDEX

Explanations

instances of the word "there" indicating existence or presence

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

elper

-0.17

-0.16

_Handler

-0.15

istar

-0.15

ler

-0.14

pler

-0.14

rier

-0.14

 apparently

-0.14

POSITIVE LOGITS

Destructor

0.15

atti

0.15

gue

0.14

ester

0.14

tÃ¼

0.14

 then

0.14

ugas

0.14

Ìģt

0.14

á»Ļt

0.14

odge

0.13

Activations Density 0.036%

instances of the word "there" indicating existence or presence

No Comments

No Known Activations

instances of the word "there" indicating existence or presence

No Comments

No Known Activations