INDEX

Explanations

terms related to decay processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

HEST

-0.16

paring

-0.15

aru

-0.15

ValuePair

-0.15

pare

-0.15

iod

-0.14

WER

-0.14

saldo

-0.14

udder

-0.14

athers

-0.14

POSITIVE LOGITS

_planes

0.16

cept

0.15

emem

0.15

iÃ§

0.14

ForMember

0.14

fcn

0.14

orage

0.13

eg

0.13

ìľ¨

0.13

lege

0.13

Activations Density 0.004%

terms related to decay processes

No Comments

No Known Activations