INDEX

Explanations

references to identity and personal history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

hiba

-0.17

uzzi

-0.16

IFO

-0.16

 __("

-0.15

ecut

-0.15

ELS

-0.15

à¸«à¸Ļ

-0.15

rios

-0.15

á»Ľ

-0.14

ebo

-0.14

POSITIVE LOGITS

0.16

is

0.15

 invention

0.15

 invented

0.13

McA

0.13

 Ð²Ð°ÑĢ

0.13

 hale

0.13

ë§¥

0.13

Activations Density 0.028%

references to identity and personal history

No Comments

No Known Activations