INDEX

Explanations

references to geographical regions or areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aign

-0.17

speaker

-0.17

áº¿p

-0.16

joy

-0.16

pts

-0.15

ufen

-0.15

wow

-0.15

apt

-0.14

ÐµÑı

-0.14

raid

-0.14

POSITIVE LOGITS

ally

0.43

als

0.32

ality

0.28

ALLY

0.27

naires

0.24

/global

0.24

/local

0.24

naire

0.24

nal

0.23

PLICIT

0.21

Activations Density 0.026%

references to geographical regions or areas

No Comments

No Known Activations