INDEX

Explanations

occurrences of words related to publication and media appearances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

istrovstvÃŃ

-0.15

æľºåħ³

-0.14

ocha

-0.14

ached

-0.14

quote

-0.14

à¹Īà¸³

-0.14

lk

-0.14

aka

-0.14

ette

-0.13

POSITIVE LOGITS

.semantic

0.15

oga

0.15

CHED

0.14

ÙĬØ«

0.14

æİ¨

0.14

à¤¾à¤¯à¤¨

0.14

 Hann

0.14

unden

0.14

onces

0.13

-buttons

0.13

Activations Density 0.006%

occurrences of words related to publication and media appearances

No Comments

No Known Activations