INDEX

Explanations

references to countries and associated 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

efs

-0.16

OF

-0.15

 Pers

-0.14

æ¸Ī

-0.14

-0.13

obia

-0.13

ÑĥÐ¶

-0.13

insk

-0.13

ofs

-0.13

ukkit

-0.13

POSITIVE LOGITS

.scalablytyped

0.16

ifar

0.16

otec

0.15

pare

0.15

Ø±ÙĪØ²

0.15

oley

0.15

erp

0.15

irie

0.14

ering

0.14

dag

0.14

Activations Density 0.015%

references to countries and associated proper nouns

No Comments

No Known Activations