INDEX

Explanations

references to tails in various contexts

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

ubat

-0.16

ester

-0.15

Î¹Î²

-0.15

ancellationToken

-0.15

ects

-0.15

ampil

-0.15

ession

-0.14

och

-0.14

ohana

-0.14

POSITIVE LOGITS

 tail

0.18

unta

0.17

UED

0.17

Tail

0.17

ersh

0.16

ëŁ¬

0.16

most

0.16

ardi

0.16

_iff

0.15

ãĥ³ãĥĩ

0.15

Activations Density 0.008%

references to tails in various contexts

No Comments

No Known Activations