INDEX

Explanations

references to abilities and mechanics within a game context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

orum

-0.17

zÅĳ

-0.14

 Palest

-0.14

ensem

-0.14

StackTrace

-0.14

Avatar

-0.14

 inject

-0.13

Ĩ

-0.13

æĴ

-0.13

à¸Ńà¸Ķ

-0.13

POSITIVE LOGITS

 platforms

0.17

 Platforms

0.17

Platforms

0.16

gnore

0.16

-platform

0.16

platform

0.15

oler

0.15

 platform

0.15

_platform

0.15

 room

0.15

Activations Density 0.018%

references to abilities and mechanics within a game context

No Comments

No Known Activations