INDEX

Explanations

terms related to morphology and its characteristics

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

ut

-0.17

TAG

-0.15

ee

-0.14

uti

-0.14

onn

-0.14

.DataTable

-0.13

 nghiÃªm

-0.13

oha

-0.13

ori

-0.13

POSITIVE LOGITS

lok

0.15

NotAllowed

0.15

reator

0.14

drv

0.14

.us

0.14

pls

0.14

chwitz

0.14

essel

0.14

lox

0.14

AZE

0.14

Activations Density 0.014%

terms related to morphology and its characteristics

No Comments

No Known Activations