INDEX

Explanations

references to taking action in response to various issues or crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

TR

-0.15

arge

-0.14

inea

-0.14

ongs

-0.14

vidence

-0.14

elder

-0.14

asti

-0.13

tryside

-0.13

TRA

-0.13

ayer

-0.13

POSITIVE LOGITS

 action

0.19

 towards

0.18

 actions

0.18

 ACTION

0.18

.ACTION

0.18

/action

0.17

-actions

0.17

(action

0.17

 Action

0.17

-action

0.17

Activations Density 0.083%

references to taking action in response to various issues or crises

No Comments

No Known Activations