INDEX

Explanations

names and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

mour

-0.15

avier

-0.14

antt

-0.14

emu

-0.14

ìĹŃ

-0.14

ebb

-0.13

ETCH

-0.13

odes

-0.13

aleb

-0.13

esco

-0.13

POSITIVE LOGITS

ercul

0.15

Wed

0.14

lfw

0.14

nock

0.14

_SPI

0.14

-animation

0.14

anke

0.14

(IService

0.13

ezier

0.13

Activations Density 0.053%

names and proper nouns

No Comments

No Known Activations