INDEX

Explanations

customer feedback and ratings about products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ø°

-0.15

icus

-0.14

 Citation

-0.14

 Shack

-0.14

icker

-0.14

uby

-0.13

dee

-0.13

Unary

-0.13

athan

-0.13

 Bernstein

-0.13

POSITIVE LOGITS

CTX

0.16

 pres

0.14

implify

0.14

keletal

0.14

 Fits

0.14

Fit

0.14

ensa

0.14

 Morr

0.14

Ä±zÄ±

0.14

rewrite

0.13

Activations Density 0.004%

customer feedback and ratings about products or services

No Comments

No Known Activations