INDEX

Explanations

references to a specific type of language or grammatical structure related to Swedish or Scandinavian terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

sea

-0.17

miss

-0.15

 Ð·Ð°ÑģÑĤ

-0.14

undy

-0.14

ancode

-0.14

missible

-0.14

oÅ¾

-0.14

hest

-0.14

 missed

-0.13

arpa

-0.13

POSITIVE LOGITS

kaar

0.17

etler

0.15

uche

0.15

 Mahm

0.14

Ð¾ÑĢÐ¾Ð½Ð¸

0.13

_serialize

0.13

ayscale

0.13

ë§Į

0.13

emann

0.13

 GlobalKey

0.13

Activations Density 0.006%

references to a specific type of language or grammatical structure related to Swedish or Scandinavian terms

No Comments

No Known Activations