INDEX

Explanations

references to significant literary figures and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

ultz

-0.15

indre

-0.14

isor

-0.14

uen

-0.14

igest

-0.14

.VideoCapture

-0.14

reme

-0.14

olumn

-0.14

 clip

-0.13

POSITIVE LOGITS

 Wilde

0.26

 Oscar

0.22

 Brow

0.22

Alg

0.21

 Christina

0.21

 decad

0.21

Sw

0.20

Rus

0.20

Rus

0.20

 Covent

0.19

Activations Density 0.027%

references to significant literary figures and their works

No Comments

No Known Activations