INDEX

Explanations

mentions of attendance or presence at events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

WARN

-0.16

arde

-0.15

vie

-0.14

sis

-0.14

Mounted

-0.14

à¸§à¸¢

-0.14

istra

-0.14

zdy

-0.13

allet

-0.13

acon

-0.13

POSITIVE LOGITS

 along

0.16

Å¾i

0.16

Ð»Ð°Ð³Ð°

0.14

 kÃ¶ÅŁ

0.14

 early

0.14

joining

0.14

 majors

0.13

?>>

0.13

ehr

0.13

gew

0.13

Activations Density 0.077%

mentions of attendance or presence at events

No Comments

No Known Activations