INDEX

Explanations

sentences related to furniture and its features

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

Ã¹

-0.15

 Coul

-0.15

iese

-0.15

azzi

-0.15

itti

-0.15

enses

-0.15

ammad

-0.15

ummer

-0.14

ocket

-0.14

POSITIVE LOGITS

chest

0.16

ãģĤãģ£ãģŁ

0.15

ISIBLE

0.14

Ð½Ð¾Ð¶

0.14

áº¿

0.14

bracht

0.14

MUX

0.14

ETERS

0.13

áº¾

0.13

ctp

0.13

Activations Density 0.089%

sentences related to furniture and its features

No Comments

No Known Activations