INDEX

Explanations

occurrences of the word "super" 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

adoo

-0.18

say

-0.17

sch

-0.17

sie

-0.16

score

-0.16

sko

-0.16

serv

-0.16

sa

-0.15

dog

-0.15

surf

-0.15

POSITIVE LOGITS

conduct

0.46

fluid

0.34

 conducting

0.30

 conduct

0.28

 conductivity

0.26

current

0.25

posed

0.25

 Conduct

0.24

 conducts

0.23

 conductor

0.23

Activations Density 0.005%

occurrences of the word "super" in various contexts

No Comments

No Known Activations