INDEX

Explanations

comparative phrases indicating a higher degree or intensity

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

eyim

-0.17

oord

-0.15

.SIG

-0.15

.scalablytyped

-0.14

ityEngine

-0.14

å½±

-0.14

ATRIX

-0.14

omi

-0.14

AINS

-0.14

ÑĤÐµÐ½

-0.14

POSITIVE LOGITS

lund

0.16

aravel

0.15

icut

0.15

tank

0.14

icina

0.14

toa

0.14

SIL

0.14

aise

0.14

_bd

0.14

 Voyager

0.14

Activations Density 0.023%

comparative phrases indicating a higher degree or intensity

No Comments

No Known Activations