INDEX

Explanations

terms related to transformation and personal change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

roke

-0.16

bourg

-0.15

ermann

-0.15

raman

-0.15

ä»½

-0.14

æĸĹ

-0.14

emm

-0.14

erman

-0.14

pch

-0.14

ITOR

-0.14

POSITIVE LOGITS

ative

0.18

ively

0.17

 Äĳá»ķi

0.16

iert

0.16

atic

0.15

oment

0.15

AllWindows

0.15

Ļæ±Ł

0.14

/trans

0.14

nemonic

0.14

Activations Density 0.015%

terms related to transformation and personal change

No Comments

No Known Activations