INDEX

Explanations

expressions of surprise or realization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

apo

-0.18

ãĥ¼ãĥĭ

-0.17

apor

-0.17

icator

-0.16

fik

-0.15

ero

-0.15

ators

-0.15

encer

-0.15

eways

-0.15

_OC

-0.14

POSITIVE LOGITS

annes

0.17

 bother

0.16

 snap

0.16

 Snap

0.16

yes

0.15

irsch

0.15

rens

0.15

sm

0.15

 yeah

0.14

Äįan

0.14

Activations Density 0.015%

expressions of surprise or realization

No Comments

No Known Activations