INDEX

Explanations

sentences with punctuation marks, particularly periods and dashes, indicating significant separations or shifts in thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Trap

-0.18

ume

-0.14

_PROC

-0.14

lil

-0.14

ungeon

-0.14

à¸´à¸§

-0.14

liest

-0.13

astos

-0.13

lj

-0.13

trinsic

-0.13

POSITIVE LOGITS

0.15

oni

0.15

alking

0.14

à¸ĩà¸ģ

0.14

enton

0.14

heimer

0.13

 Marcel

0.13

oeff

0.13

arry

0.13

Activations Density 0.094%

sentences with punctuation marks, particularly periods and dashes, indicating significant separations or shifts in thoughts

No Comments

No Known Activations