INDEX

Explanations

terms related to cognitive processes and abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lo

-0.19

dy

-0.16

loff

-0.15

ivative

-0.15

patrick

-0.15

ady

-0.15

tem

-0.14

.transitions

-0.14

uth

-0.14

licht

-0.14

POSITIVE LOGITS

-be

0.22

/memory

0.17

 decline

0.17

 functioning

0.15

 Decl

0.15

 impairment

0.15

 reserve

0.15

enh

0.15

Vig

0.15

 Bite

0.15

Activations Density 0.007%

terms related to cognitive processes and abilities

No Comments

No Known Activations