INDEX

Explanations

instances of the letter 'o' 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ap

-0.15

 Jennings

-0.15

 Sheldon

-0.15

tn

-0.15

Configurer

-0.14

ller

-0.14

 Plug

-0.14

 Corner

-0.14

POSITIVE LOGITS

rait

0.16

Desk

0.15

áºł

0.14

 ãĢĪ

0.14

Ð»Ð°Ð½Ð´

0.13

"><!--

0.13

isch

0.13

 ActionTypes

0.13

 Morris

0.13

gili

0.13

Activations Density 0.000%

instances of the letter 'o' in various contexts

No Comments

No Known Activations