INDEX

Explanations

specific sequences of letters and sounds indicating names or titles

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

 Morrow

-0.15

 hers

-0.15

usc

-0.15

utenberg

-0.14

ahoo

-0.14

bid

-0.14

Bid

-0.14

orb

-0.14

otos

-0.14

harma

-0.14

POSITIVE LOGITS

acter

0.16

aub

0.16

lastic

0.16

isseur

0.15

artz

0.15

itsu

0.15

Ĺi

0.15

@Resource

0.14

pf

0.14

 Donovan

0.14

Activations Density 0.030%

specific sequences of letters and sounds indicating names or titles

No Comments

No Known Activations