INDEX

Explanations

instances of the word "make" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ockets

-0.15

iedad

-0.15

oose

-0.15

åĲĪãĤıãģĽ

-0.14

ich

-0.14

Ð²Ð°Ð´

-0.14

Ä±c

-0.14

ÛĮÙĨÚ©

-0.14

_PG

-0.14

åºĹ

-0.14

POSITIVE LOGITS

 sense

0.23

 headlines

0.18

 Sense

0.17

 senses

0.17

sense

0.16

Sense

0.15

iple

0.15

turnstile

0.14

me

0.14

 sentido

0.14

Activations Density 0.070%

instances of the word "make" and its variations in various contexts

No Comments

No Known Activations