INDEX

Explanations

references to food and recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

urette

-0.18

ANGER

-0.17

bindung

-0.15

Ð²Ð¸ÑĤ

-0.15

anger

-0.15

 liaison

-0.14

Äįer

-0.14

rem

-0.14

.Utc

-0.14

ÑīÐ¸Ð½

-0.14

POSITIVE LOGITS

unce

0.16

pch

0.15

 Morris

0.14

ocab

0.14

ingo

0.14

tgl

0.14

ond

0.14

pline

0.13

 inplace

0.13

Activations Density 0.014%

references to food and recipes

No Comments

No Known Activations