INDEX

Explanations

elements related to dialogue and conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.17

IZER

-0.16

oug

-0.14

din

-0.14

ainties

-0.14

sj

-0.14

_defs

-0.13

kate

-0.13

ANCE

-0.13

RESOURCE

-0.13

POSITIVE LOGITS

.ht

0.15

ama

0.15

 Hell

0.15

hangi

0.14

 hell

0.14

Set

0.14

 Barker

0.14

pij

0.14

0.13

"crypto

0.13

Activations Density 0.054%

elements related to dialogue and conversation

No Comments

No Known Activations