INDEX

Explanations

details related to cooking instructions and ingredients

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

ente

-0.15

é¥

-0.14

gger

-0.14

.sponge

-0.14

regnum

-0.13

ÑĻ

-0.13

ordin

-0.13

eva

-0.13

avy

-0.13

yntax

-0.13

POSITIVE LOGITS

 mixture

0.22

ixture

0.16

ROWS

0.16

heiro

0.16

indow

0.14

_TERMIN

0.14

tres

0.14

iyi

0.14

Reserved

0.14

_Enter

0.14

Activations Density 0.041%

details related to cooking instructions and ingredients

No Comments

No Known Activations