INDEX

Explanations

metrics related to health assessments and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lep

-0.16

illard

-0.16

iaux

-0.16

lac

-0.15

ÏģÎ¿Ïħ

-0.14

ACITY

-0.14

agar

-0.14

 hotter

-0.13

 Maher

-0.13

ãĥªãĤ¢

-0.13

POSITIVE LOGITS

 medium

0.55

 Medium

0.49

medium

0.49

Medium

0.47

 intermediate

0.40

 moderate

0.40

-medium

0.39

 Moderate

0.36

 Intermediate

0.36

_medium

0.35

Activations Density 0.237%

metrics related to health assessments and evaluations

No Comments

No Known Activations