INDEX

Explanations

references to tea and tea-related products or experiences

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

ÑĬ

-0.17

ted

-0.17

cha

-0.17

heim

-0.16

so

-0.16

er

-0.16

eds

-0.16

POSITIVE LOGITS

ierz

0.17

à¸£à¸Ķ

0.16

ÎŃÏģÎ±

0.16

idlo

0.16

mamak

0.15

zier

0.15

asaki

0.15

Æ°á»Ľng

0.15

obili

0.15

ÄĽÅĻ

0.15

Activations Density 0.010%

references to tea and tea-related products or experiences

No Comments

No Known Activations