INDEX

Explanations

references to the color red or related concepts

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

boru

-0.21

dna

-0.18

dro

-0.16

ÎµÎ¯Î¿

-0.15

hend

-0.15

teki

-0.15

kok

-0.15

dale

-0.14

ebo

-0.14

 Charg

-0.14

POSITIVE LOGITS

ress

0.31

raft

0.30

 tape

0.28

 flag

0.26

istrict

0.26

ressing

0.25

-flag

0.25

 flags

0.24

ocument

0.24

resses

0.24

Activations Density 0.011%

references to the color red or related concepts

No Comments

No Known Activations