INDEX

Explanations

instances of adjectives describing the quality or condition of nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ses

-0.18

ologies

-0.16

 Ð±Ð¾Ð»ÑĮÑĪÐ¾Ð¹

-0.14

opal

-0.14

odont

-0.14

ories

-0.14

ÏģÎ¯Î¿Ïħ

-0.14

Ð¸ÑĩÐµÑģÐºÐ¾Ðµ

-0.14

urations

-0.14

 jednoho

-0.14

POSITIVE LOGITS

ottie

0.15

.opens

0.14

param

0.14

iona

0.14

ÑģÑĤÑİ

0.14

 convict

0.14

.ERR

0.14

 ÑģÑĢÐµÐ´ÑģÑĤÐ²Ð°

0.13

esta

0.13

rega

0.13

Activations Density 0.029%

instances of adjectives describing the quality or condition of nouns

No Comments

No Known Activations