INDEX

Explanations

references to poetry and literary elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Ø§ÙĦØ¹Ø¸

-0.15

reff

-0.15

å¾®è½¯éĽħé»ĳ

-0.15

heimer

-0.15

ëį°ìĿ´íĬ¸

-0.15

rozen

-0.14

ynes

-0.14

Ð¾Ð±Ð¾Ð²

-0.14

Ð¿Ð¸Ð¾Ð½

-0.14

svp

-0.14

POSITIVE LOGITS

0.16

 cunt

0.15

çµ¡

0.14

 Plex

0.14

 Dickinson

0.14

0.13

wd

0.13

etro

0.13

Mn

0.13

Activations Density 0.287%

references to poetry and literary elements

No Comments

No Known Activations