INDEX

Explanations

names of characters and actors in the context of films

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

osph

-0.16

lymp

-0.15

atch

-0.15

noinspection

-0.15

elib

-0.15

å¤§äºº

-0.14

splice

-0.14

Ð¿Ð°ÑĤ

-0.14

.nano

-0.14

iah

-0.14

POSITIVE LOGITS

onet

0.15

 Acting

0.14

jspx

0.14

ht

0.14

Ìģ

0.13

less

0.13

.ul

0.13

izik

0.13

.IsNullOr

0.13

iov

0.13

Activations Density 0.094%

names of characters and actors in the context of films

No Comments

No Known Activations