INDEX

Explanations

symbolic representations of food and cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

asley

-0.16

paque

-0.16

pedia

-0.16

rippling

-0.15

iked

-0.14

ANA

-0.14

athi

-0.14

aura

-0.13

ampion

-0.13

ÏħÎ³

-0.13

POSITIVE LOGITS

ÐºÐ°Ñģ

0.16

ãĤ«ãĥ«

0.15

abet

0.15

çĶ²

0.14

liner

0.14

abyrinth

0.14

iet

0.13

µľ

0.13

ixon

0.13

liv

0.13

Activations Density 0.009%

symbolic representations of food and cooking instructions

No Comments

No Known Activations