INDEX

Explanations

words or phrases associated with significant life events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

val

-0.14

_cre

-0.14

uple

-0.14

aw

-0.14

onical

-0.14

å·®

-0.14

/ajax

-0.14

heed

-0.14

 Journalism

-0.13

Fd

-0.13

POSITIVE LOGITS

ovich

0.15

Äįel

0.15

berman

0.14

lies

0.14

anmar

0.14

æľ¯

0.13

ersiz

0.13

/System

0.13

/Area

0.13

Activations Density 0.173%

words or phrases associated with significant life events

No Comments

No Known Activations