INDEX

Explanations

punctuation marks and emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Suddenly

-0.15

uisse

-0.14

YM

-0.14

ãĥķãĤ§

-0.14

ToLocal

-0.14

iye

-0.14

ãģªãģĹ

-0.13

ursal

-0.13

egin

-0.13

Specifier

-0.13

POSITIVE LOGITS

0.17

 Inst

0.16

0.15

 Gods

0.15

 istiyor

0.14

part

0.14

Sys

0.14

Inst

0.14

appa

0.14

 Ment

0.14

Activations Density 0.209%

punctuation marks and emotional expressions

No Comments

No Known Activations