INDEX

Explanations

occurrences of the word "on" in relation to reflective or thoughtful contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ilim

-0.14

atables

-0.14

 Ø¨ÙĬ

-0.14

out

-0.14

ongan

-0.14

ying

-0.14

-answer

-0.14

/pg

-0.14

yna

-0.13

(TM

-0.13

POSITIVE LOGITS

ewater

0.14

xfd

0.14

inheritDoc

0.14

ennen

0.14

çĶ²

0.14

afka

0.14

olta

0.14

ngÃ¶r

0.13

adm

0.13

paz

0.13

Activations Density 0.013%

occurrences of the word "on" in relation to reflective or thoughtful contexts

No Comments

No Known Activations