INDEX

Explanations

phrases indicating emotional states or interactions with others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inic

-0.14

poc

-0.14

esis

-0.14

æ¢

-0.13

">//

-0.13

regn

-0.13

 Vaughan

-0.13

MAS

-0.12

Å¡ti

-0.12

ivre

-0.12

POSITIVE LOGITS

Spell

0.15

arf

0.15

anan

0.15

ringe

0.14

omba

0.14

spell

0.14

eda

0.14

ï»¿↵↵

0.13

lif

0.13

rots

0.13

Activations Density 0.177%

phrases indicating emotional states or interactions with others

No Comments

No Known Activations

phrases indicating emotional states or interactions with others

No Comments

No Known Activations