INDEX

Explanations

references to characters or names associated with specific stories or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.16

umas

-0.16

acen

-0.16

OID

-0.15

uality

-0.14

acists

-0.14

akov

-0.14

oggle

-0.14

ayout

-0.14

POSITIVE LOGITS

efeller

0.18

ledge

0.17

.RunWith

0.15

iginal

0.15

Ro

0.15

aldo

0.15

ario

0.14

ro

0.14

cea

0.14

-ro

0.14

Activations Density 0.033%

references to characters or names associated with specific stories or narratives

No Comments

No Known Activations