INDEX

Explanations

terminology related to game mechanics and character attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

æ¡

-0.16

yte

-0.15

ovu

-0.15

 republika

-0.14

å¼¥

-0.14

.yahoo

-0.14

MOTE

-0.14

geÃ§

-0.14

etro

-0.14

 rein

-0.14

POSITIVE LOGITS

0.17

.setViewport

0.15

yor

0.14

 Fres

0.14

cle

0.14

0.13

essel

0.13

ouz

0.13

Activations Density 0.025%

terminology related to game mechanics and character attributes

No Comments

No Known Activations