INDEX

Explanations

variations of the word "I" and references to interpersonal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ogg

-0.16

 realised

-0.15

 SavaÅŁ

-0.15

oenix

-0.15

felt

-0.15

chaft

-0.14

-valu

-0.14

.tell

-0.14

 becomes

-0.14

 realise

-0.14

POSITIVE LOGITS

 belong

0.17

ÑĸÐ¼Ñĸ

0.16

 belongs

0.15

Ð»Ð°Ð³Ð¾Ð´

0.14

 indeed

0.14

areth

0.14

dot

0.14

æĺ¯åľ¨

0.14

Activations Density 0.265%

variations of the word "I" and references to interpersonal relationships

No Comments

No Known Activations