INDEX

Explanations

personal pronouns and references to ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

isos

-0.15

-0.14

 implication

-0.14

 constraint

-0.14

èĪ¬

-0.14

Ð¹

-0.13

ç¸

-0.13

allen

-0.13

tera

-0.13

sl

-0.13

POSITIVE LOGITS

 approach

0.19

 reign

0.16

 presence

0.15

 career

0.15

appro

0.15

 ActionTypes

0.15

ichni

0.14

oleon

0.14

 existence

0.14

 mission

0.14

Activations Density 0.266%

personal pronouns and references to ownership

No Comments

No Known Activations