INDEX

Explanations

references to "chains" in various contexts, including literal and metaphorical uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

onas

-0.19

±

-0.17

hone

-0.16

ync

-0.15

rawer

-0.15

aurus

-0.15

ieties

-0.14

arians

-0.14

/change

-0.14

POSITIVE LOGITS

alysis

0.22

-link

0.22

 reaction

0.21

 link

0.20

Reaction

0.20

 Reaction

0.19

ings

0.18

-chain

0.18

mail

0.18

apple

0.18

Activations Density 0.016%

references to "chains" in various contexts, including literal and metaphorical uses

No Comments

No Known Activations