INDEX

Explanations

variations of the word "met" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

APPER

-0.18

éĻµ

-0.15

 bekan

-0.15

apper

-0.15

phe

-0.14

alim

-0.14

 Haupt

-0.14

ipur

-0.14

idget

-0.14

bem

-0.14

POSITIVE LOGITS

eking

0.16

ropolis

0.15

abolic

0.14

Sul

0.14

pch

0.14

avings

0.14

lify

0.14

abol

0.14

ikit

0.14

Activations Density 0.025%

variations of the word "met" in different contexts

No Comments

No Known Activations