INDEX

Explanations

terms related to brain monitoring and stimulation techniques

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

 Singer

-0.16

ampo

-0.14

çŃĴ

-0.14

Ø¨Ø§

-0.14

 chalk

-0.14

alley

-0.14

arella

-0.14

chure

-0.14

ulace

-0.14

atis

-0.13

POSITIVE LOGITS

RAINT

0.16

Typ

0.15

CPP

0.14

 summ

0.14

FG

0.14

olly

0.13

dol

0.13

ihn

0.13

_GEN

0.13

Activations Density 0.009%

terms related to brain monitoring and stimulation techniques

No Comments

No Known Activations