INDEX

Explanations

occurrences of the word "Bre" and its variations, often indicating a focus on particular topics or names associated with that prefix

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

one

-0.15

å²

-0.14

éŀ

-0.14

ellite

-0.14

ÑīÐµÐ¹

-0.14

encer

-0.14

pers

-0.13

.Invalid

-0.13

ular

-0.13

POSITIVE LOGITS

bre

0.22

htaking

0.17

 vice

0.17

ault

0.17

Bre

0.17

vice

0.16

embro

0.16

 Vice

0.15

illon

0.15

dux

0.15

Activations Density 0.020%

occurrences of the word "Bre" and its variations, often indicating a focus on particular topics or names associated with that prefix

No Comments

No Known Activations