INDEX

Explanations

references to people and their associated details in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nap

-0.17

nap

-0.16

ãĤ¶ãĥ¼

-0.16

atab

-0.15

arkin

-0.15

Ð¢Ð°

-0.14

 åº¦

-0.14

hos

-0.14

 anmeld

-0.14

Nap

-0.13

POSITIVE LOGITS

çĶ

0.16

Hoy

0.16

'=>"

0.15

 Patterson

0.14

rd

0.14

antee

0.13

 prejudice

0.13

.banner

0.13

 Schultz

0.13

UFF

0.13

Activations Density 0.005%

references to people and their associated details in various contexts

No Comments

No Known Activations