INDEX

Explanations

key phrases and transitions that indicate the structure and flow of time in narrative or argumentative contexts

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

Ou

-0.16

PLIC

-0.15

isko

-0.15

[of

-0.15

uw

-0.15

.logical

-0.15

lic

-0.14

.bid

-0.14

éĻħ

-0.14

ÐµÐ²Ð¸

-0.14

POSITIVE LOGITS

end

0.25

 sonunda

0.22

.end

0.19

 ended

0.19

END

0.19

-end

0.18

 finished

0.17

_end

0.17

 cuá»ĳi

0.17

 ending

0.17

Activations Density 0.076%

key phrases and transitions that indicate the structure and flow of time in narrative or argumentative contexts

No Comments

No Known Activations