INDEX

Explanations

instances of reported speech or dialogue

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

ãģŁãĤģãģ®

-0.15

azard

-0.14

iller

-0.13

rane

-0.13

 yourselves

-0.13

plus

-0.13

quan

-0.12

ãģķãģĽ

-0.12

they

-0.12

 ÙĦÙĥØ±Ø©

-0.12

POSITIVE LOGITS

 said

0.16

 spokesman

0.15

aukee

0.14

ãĤ´ãĥª

0.14

AllowAnonymous

0.13

 spokeswoman

0.13

:\/\/

0.13

 added

0.13

iddi

0.13

Activations Density 0.097%

instances of reported speech or dialogue

No Comments

No Known Activations