INDEX

Explanations

proper names or identifiers such as author names and institutions associated with scientific papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 acronym

-0.14

orthand

-0.14

Lob

-0.14

 Inflate

-0.14

 JÃ¡

-0.14

ldkf

-0.14

zos

-0.13

à¤°

-0.13

elow

-0.13

tvrt

-0.13

POSITIVE LOGITS

0.14

ÃĹ↵↵

0.14

unu

0.14

llib

0.14

ï¿¥

0.14

fter

0.14

.ReadString

0.13

à¸ĵ

0.13

igit

0.13

Activations Density 0.106%

proper names or identifiers such as author names and institutions associated with scientific papers

No Comments

No Known Activations