INDEX

Explanations

actions related to adding, mixing, or preparing food ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ighth

-0.14

ë³µ

-0.14

nut

-0.14

kas

-0.14

zos

-0.14

 ÑĥÐ»ÑĥÑĩ

-0.14

Ã³r

-0.13

zig

-0.13

enthal

-0.13

aviors

-0.13

POSITIVE LOGITS

heck

0.15

olls

0.15

 indication

0.14

(es

0.14

gos

0.14

agi

0.14

Ð»ÑĥÐ³Ð¸

0.13

hetto

0.13

 indicates

0.13

 indications

0.13

Activations Density 0.155%

actions related to adding, mixing, or preparing food ingredients

No Comments

No Known Activations