INDEX

Explanations

references to measurement and evaluation metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Î²Î¿

-0.16

eniable

-0.15

osity

-0.15

åı·

-0.15

aper

-0.15

ias

-0.15

à¸§à¸¢

-0.14

ionage

-0.14

POSITIVE LOGITS

 diagonal

0.15

Cad

0.15

china

0.15

/umd

0.14

onor

0.14

 Äĳá»ĭa

0.14

recht

0.14

ivot

0.14

``(

0.14

Eag

0.14

Activations Density 0.018%

references to measurement and evaluation metrics

No Comments

No Known Activations