INDEX

Explanations

quantifiable metrics and assessments related to performance and progress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aris

-0.14

 norge

-0.13

lessly

-0.13

asper

-0.13

reso

-0.12

ky

-0.12

è¦§

-0.12

 things

-0.12

 treff

-0.12

reau

-0.12

POSITIVE LOGITS

XHR

0.13

ourcem

0.12

 Herb

0.12

stice

0.11

$$$$

0.11

Vendor

0.11

Activations Density 0.076%

quantifiable metrics and assessments related to performance and progress

No Comments

No Known Activations