INDEX

Explanations

instances of the word "people" and related discussions about individuals and groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ã¦kke

-0.16

meer

-0.15

duk

-0.15

à¹Ģà¸Ńà¸ĩ

-0.15

GGLE

-0.14

 Serge

-0.14

.nlm

-0.14

agina

-0.14

stadt

-0.14

oreach

-0.14

POSITIVE LOGITS

 talk

0.21

 died

0.18

 dying

0.17

 talking

0.16

 forget

0.16

 dies

0.15

say

0.15

Talk

0.15

who

0.15

à¹Ĥà¸Ĺ

0.15

Activations Density 0.156%

instances of the word "people" and related discussions about individuals and groups

No Comments

No Known Activations