INDEX

Explanations

references to places, particularly parks and recreational areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

è¡Ĺ

-0.15

eres

-0.14

plib

-0.14

STA

-0.13

Mul

-0.13

IPS

-0.13

 canal

-0.13

_PORTS

-0.13

ateria

-0.13

Mul

-0.13

POSITIVE LOGITS

adoo

0.17

.edu

0.17

-area

0.15

ucumber

0.15

 itself

0.15

 Resort

0.14

obia

0.14

Æ¯á»

0.14

 Authority

0.14

 Visitor

0.14

Activations Density 0.163%

references to places, particularly parks and recreational areas

No Comments

No Known Activations