INDEX

Explanations

references to personal identity and relationships

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

phia

-0.16

ible

-0.16

arma

-0.15

 ÑĥÐ³Ð¾Ð´

-0.15

nton

-0.15

onis

-0.15

 Goodman

-0.15

rame

-0.15

 hydrated

-0.15

odge

-0.15

POSITIVE LOGITS

oft

0.18

é®

0.16

otor

0.15

eter

0.15

.yy

0.15

eness

0.14

 freel

0.14

et

0.13

 dual

0.13

å¯¿

0.13

Activations Density 0.150%

references to personal identity and relationships

No Comments

No Known Activations