INDEX

Explanations

references to furniture and related items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aci

-0.15

assis

-0.15

çłģ

-0.15

unto

-0.15

vro

-0.15

/topics

-0.15

lys

-0.14

uck

-0.14

quine

-0.14

eba

-0.13

POSITIVE LOGITS

oten

0.14

alet

0.14

-addons

0.14

lerce

0.14

ists

0.14

 <!--[

0.14

ilerden

0.14

agan

0.13

amental

0.13

cla

0.13

Activations Density 0.006%

references to furniture and related items

No Comments

No Known Activations