INDEX

Explanations

references to resistance 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ystone

-0.21

ings

-0.20

inged

-0.17

shots

-0.16

INGS

-0.16

tra

-0.16

seed

-0.15

ãĥ£

-0.15

obi

-0.15

HEMA

-0.15

POSITIVE LOGITS

ive

0.24

ances

0.19

ively

0.19

 against

0.19

/res

0.18

eenth

0.17

-ce

0.17

à¸Ĺà¸²à¸Ļ

0.17

 fighters

0.17

ivec

0.17

Activations Density 0.018%

references to resistance in various contexts

No Comments

No Known Activations