INDEX

Explanations

mentions of significant buildings or institutions, particularly those referred to as "House."

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

OSH

-0.17

xes

-0.16

unya

-0.15

ountry

-0.14

_lifetime

-0.14

esub

-0.14

Industrial

-0.14

ces

-0.13

ksi

-0.13

POSITIVE LOGITS

.Formatter

0.16

andles

0.16

breaking

0.15

Lew

0.15

LEAN

0.15

endir

0.15

link

0.14

æ°ĳæĹı

0.14

broken

0.14

bj

0.14

Activations Density 0.007%

mentions of significant buildings or institutions, particularly those referred to as "House."

No Comments

No Known Activations