INDEX

Explanations

occurrences of the word "New" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ocop

-0.16

orum

-0.14

lez

-0.14

oga

-0.13

ulary

-0.13

agus

-0.13

Bed

-0.13

OG

-0.13

.Abs

-0.13

inerary

-0.13

POSITIVE LOGITS

vem

0.20

 MyBase

0.17

arkers

0.15

ÐµÑĢÐ°Ð»ÑĮ

0.15

 permanent

0.15

ãĥĢãĤ¤

0.15

=forms

0.15

ison

0.14

eneg

0.14

INA

0.14

Activations Density 0.035%

occurrences of the word "New" in various contexts

No Comments

No Known Activations