INDEX

Explanations

directions and instructions for navigating to a specific location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Î¿Ïį

-0.16

Î²Î¿

-0.15

isch

-0.14

uids

-0.14

=yes

-0.14

uci

-0.14

ulet

-0.14

æķ·

-0.14

imer

-0.14

 Knight

-0.14

POSITIVE LOGITS

å£«

0.16

iyon

0.16

curity

0.15

malink

0.14

COPY

0.14

-answer

0.13

ä¹ħ

0.13

dog

0.13

dog

0.13

rame

0.13

Activations Density 0.383%

directions and instructions for navigating to a specific location

No Comments

No Known Activations