INDEX

Explanations

terms associated with heroism or heroic qualities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

phia

-0.17

Pik

-0.17

NAL

-0.16

axon

-0.15

 Aust

-0.15

 xanh

-0.15

æ¯

-0.15

agen

-0.15

tl

-0.14

Äįka

-0.14

POSITIVE LOGITS

readcr

0.15

 Lara

0.15

Wa

0.15

į¨

0.15

Wa

0.15

 bios

0.14

vet

0.14

ampo

0.14

egl

0.14

 cÃ©lib

0.14

Activations Density 0.015%

terms associated with heroism or heroic qualities

No Comments

No Known Activations