INDEX

Explanations

relationships and references to family

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orks

-0.18

enk

-0.15

Ð½Ð¾ÑĪ

-0.15

.sy

-0.14

atte

-0.14

-bars

-0.14

contres

-0.14

kok

-0.14

indows

-0.14

upport

-0.14

POSITIVE LOGITS

åı

0.14

uggle

0.13

ìĹŃ

0.13

 prepar

0.13

band

0.13

 Arbit

0.13

ufe

0.13

_LINEAR

0.13

BeNull

0.13

Activations Density 0.076%

relationships and references to family

No Comments

No Known Activations