INDEX

Explanations

inquiries and references to past experiences or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

apult

-0.15

æµľ

-0.15

_cre

-0.14

eing

-0.14

ozy

-0.14

requete

-0.13

 ReturnValue

-0.13

andy

-0.13

udent

-0.13

 Jasper

-0.13

POSITIVE LOGITS

eya

0.20

isode

0.16

ÅĤo

0.15

mont

0.15

dar

0.15

RIX

0.15

arat

0.15

_NOTICE

0.14

Ø±ÙĬÙģ

0.14

eyen

0.14

Activations Density 0.066%

inquiries and references to past experiences or observations

No Comments

No Known Activations