INDEX

Explanations

references to "Star Wars" and related iconic elements

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

aspers

-0.17

ÑıÐ¶

-0.16

ubishi

-0.16

estro

-0.16

ester

-0.16

oger

-0.15

ronics

-0.15

erson

-0.15

ìĤ¬íķŃ

-0.15

OLVE

-0.15

POSITIVE LOGITS

fish

0.22

vation

0.19

ry

0.18

light

0.18

red

0.17

0.16

SCP

0.15

burst

0.15

let

0.15

/root

0.15

Activations Density 0.054%

references to "Star Wars" and related iconic elements

No Comments

No Known Activations

references to "Star Wars" and related iconic elements

No Comments

No Known Activations