INDEX

Explanations

terms related to the nervous system and its functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

isters

-0.21

åĶĩ

-0.19

oler

-0.17

ister

-0.16

aremos

-0.15

eful

-0.15

_IT

-0.15

zung

-0.15

kap

-0.14

ãĥ£

-0.14

POSITIVE LOGITS

 endings

0.26

vous

0.23

 fiber

0.20

 fibre

0.20

 system

0.19

 fibers

0.19

fiber

0.18

 wreck

0.17

 ending

0.17

 tissue

0.17

Activations Density 0.014%

terms related to the nervous system and its functions

No Comments

No Known Activations