INDEX

Explanations

pronouns that indicate second-person and first-person perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 sobie

-0.18

box

-0.15

ually

-0.15

spor

-0.14

 Forge

-0.14

 vlas

-0.14

 Ortiz

-0.14

ildo

-0.14

mac

-0.14

paramref

-0.14

POSITIVE LOGITS

esson

0.16

è³

0.16

Pla

0.16

chooser

0.15

 tabs

0.15

ekli

0.15

rong

0.15

_tokenize

0.15

andler

0.14

 alive

0.14

Activations Density 0.025%

pronouns that indicate second-person and first-person perspectives

No Comments

No Known Activations