INDEX

Explanations

phrases and terms related to principles

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

oken

-0.18

gie

-0.17

emez

-0.17

encias

-0.15

dens

-0.15

ceph

-0.15

rait

-0.15

akan

-0.15

emp

-0.15

ney

-0.14

POSITIVE LOGITS

-agent

0.28

ities

0.19

-Agent

0.19

ps

0.18

 investigator

0.18

/pr

0.18

stown

0.17

 Investig

0.16

pal

0.16

etro

0.15

Activations Density 0.016%

phrases and terms related to principles

No Comments

No Known Activations