INDEX

Explanations

phrases indicating planning and preparation in a high-stakes context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

odzi

-0.15

é§

-0.14

ParameterValue

-0.14

odka

-0.13

Mia

-0.13

atk

-0.13

enstein

-0.13

 Tart

-0.13

insky

-0.13

 Hind

-0.13

POSITIVE LOGITS

PCs

0.19

 NPCs

0.17

 adventurers

0.16

ismatic

0.15

GM

0.15

GM

0.15

 teleport

0.15

 ausp

0.15

.persistent

0.14

 adventurer

0.14

Activations Density 0.048%

phrases indicating planning and preparation in a high-stakes context

No Comments

No Known Activations