INDEX

Explanations

phrases indicating availability and options related to purchases or access

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

owler

-0.14

æµ¦

-0.14

ibbon

-0.14

chine

-0.14

okus

-0.14

 functional

-0.14

åļ

-0.14

amble

-0.13

erti

-0.13

.ke

-0.13

POSITIVE LOGITS

mts

0.18

0.15

WARDED

0.14

roman

0.14

boro

0.14

thrown

0.14

ISMATCH

0.13

bage

0.13

Activations Density 0.047%

phrases indicating availability and options related to purchases or access

No Comments

No Known Activations