INDEX

Explanations

references to individuals and their roles in various contexts, particularly related to support and recovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

upo

-0.16

ÄĽn

-0.15

orget

-0.15

chten

-0.15

izer

-0.15

NSBundle

-0.14

eus

-0.14

Ã¼h

-0.14

/stats

-0.14

ãĥ

-0.13

POSITIVE LOGITS

 individual

0.15

bullet

0.14

etched

0.14

.converter

0.14

Lau

0.14

 oran

0.14

onth

0.13

 Ø¬ÙĨ

0.13

ola

0.13

Activations Density 0.521%

references to individuals and their roles in various contexts, particularly related to support and recovery

No Comments

No Known Activations