INDEX

Explanations

mentions of seasons, episodes, or significant events in shows or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

aland

-0.15

ilk

-0.15

 other

-0.15

_detach

-0.14

aml

-0.14

.www

-0.14

 modern

-0.14

ler

-0.14

fts

-0.14

ectl

-0.13

POSITIVE LOGITS

-era

0.18

íĸĪëįĺ

0.16

/Foundation

0.15

zung

0.14

/start

0.14

 çķĻ

0.13

enor

0.13

 Ð¿ÑĢÐ¾ÑĪ

0.13

era

0.13

ittle

0.13

Activations Density 0.189%

mentions of seasons, episodes, or significant events in shows or movies

No Comments

No Known Activations