INDEX

Explanations

words associated with research methodologies and scientific assessment

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

Ã¡g

-0.15

olla

-0.15

lamÄ±ÅŁ

-0.14

Ì£

-0.14

aa

-0.14

HEMA

-0.14

awl

-0.13

 FindObjectOfType

-0.13

_topology

-0.13

night

-0.13

POSITIVE LOGITS

 separately

0.17

èĦ

0.15

 Separate

0.15

 separate

0.15

 seperate

0.15

ome

0.14

 briefly

0.14

ascus

0.13

ikt

0.13

chied

0.13

Activations Density 0.067%

words associated with research methodologies and scientific assessment

No Comments

No Known Activations