INDEX

Explanations

terms related to the sharing and distribution of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 anywhere

-0.18

sw

-0.16

itan

-0.15

 Conce

-0.15

isel

-0.15

 conc

-0.15

idders

-0.14

kol

-0.14

oom

-0.14

itr

-0.14

POSITIVE LOGITS

Ã¶h

0.18

Ã¸re

0.17

Äįet

0.17

inus

0.15

.vocab

0.14

\D

0.14

à¸ªà¸°

0.14

Ð»Ð°ÑĪ

0.14

Activations Density 0.041%

terms related to the sharing and distribution of information

No Comments

No Known Activations