INDEX

Explanations

specific names and terms related to people, locations, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

uco

-0.17

ãĥ¼ãĥ³

-0.16

 Pist

-0.15

Î³ÎºÎ±

-0.15

ropri

-0.14

obi

-0.14

Î³ÎºÏĮ

-0.14

 DevComponents

-0.14

 Trem

-0.14

POSITIVE LOGITS

|R

0.19

ri

0.17

RA

0.17

RS

0.16

RT

0.16

RI

0.16

(R

0.15

ilda

0.15

=R

0.15

Activations Density 0.233%

specific names and terms related to people, locations, and organizations

No Comments

No Known Activations