INDEX

Explanations

instances of the word "know" and its variations, indicating familiarity or awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

erty

-0.17

ÂŃi

-0.16

.blogspot

-0.16

ynamo

-0.15

eyn

-0.15

bett

-0.15

emony

-0.15

NamedQuery

-0.15

eraÃ§Ã£o

-0.15

wik

-0.15

POSITIVE LOGITS

alte

0.15

Ð¾Ð»ÐµÑĤ

0.14

etti

0.14

aved

0.14

 through

0.14

endo

0.13

ures

0.13

afa

0.13

ArrayOf

0.13

Activations Density 0.036%

instances of the word "know" and its variations, indicating familiarity or awareness

No Comments

No Known Activations