INDEX

Explanations

words related to negative actions or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

/umd

-0.18

esser

-0.16

GuidId

-0.15

 kino

-0.14

alsy

-0.14

 Souls

-0.14

ÅĽcie

-0.14

assis

-0.14

vala

-0.14

èľĺèĽĽ

-0.14

POSITIVE LOGITS

 Club

0.23

Club

0.20

 Frozen

0.19

 Penguin

0.19

 Snow

0.18

cp

0.18

 frozen

0.18

 sled

0.18

Snow

0.18

 club

0.17

Activations Density 0.001%

words related to negative actions or consequences

No Comments

No Known Activations