INDEX

Explanations

references to high costs or expensive items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ixin

-0.16

lide

-0.16

hod

-0.15

tery

-0.14

usz

-0.14

 otherwise

-0.14

ao

-0.13

quot

-0.13

inger

-0.13

conda

-0.13

POSITIVE LOGITS

SPA

0.18

elter

0.15

Å¡ak

0.15

elper

0.15

ERV

0.15

Ã§ak

0.14

edom

0.14

.strict

0.14

endon

0.14

ARRIER

0.14

Activations Density 0.014%

references to high costs or expensive items

No Comments

No Known Activations