INDEX

Explanations

specific terminology related to various domains, such as health, finance, and leisure activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.17

oux

-0.16

rell

-0.16

Ì£

-0.15

olla

-0.14

thag

-0.13

ud

-0.13

terr

-0.13

aine

-0.13

erp

-0.13

POSITIVE LOGITS

idad

0.15

ISM

0.14

ism

0.14

istas

0.14

quat

0.13

avel

0.13

heimer

0.13

ayÄ±n

0.13

.gdx

0.13

ouncer

0.13

Activations Density 0.082%

specific terminology related to various domains, such as health, finance, and leisure activities

No Comments

No Known Activations