INDEX

Explanations

references to contacting resorts for inquiries or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ilk

-0.17

iba

-0.16

raÅ¾

-0.16

âķĳ

-0.15

ones

-0.15

alar

-0.15

uki

-0.14

aaa

-0.14

lod

-0.14

autop

-0.14

POSITIVE LOGITS

 yourselves

0.18

 independent

0.16

cision

0.16

orb

0.16

opensource

0.15

Ð²Ð°Ð²

0.15

 independently

0.15

 elsewhere

0.14

 whatever

0.14

iÃ©n

0.14

Activations Density 0.236%

references to contacting resorts for inquiries or assistance

No Comments

No Known Activations