INDEX

Explanations

nouns and phrases related to areas, locations, and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ostel

-0.14

avier

-0.14

RootElement

-0.13

released

-0.13

vise

-0.13

ctp

-0.13

ried

-0.13

áº¯t

-0.13

untu

-0.13

-0.12

POSITIVE LOGITS

 inhabited

0.44

 frequ

0.43

 occupied

0.41

 populated

0.37

occupied

0.34

 where

0.33

 visited

0.30

 overrun

0.30

 housing

0.30

 hosting

0.29

Activations Density 0.529%

nouns and phrases related to areas, locations, and communities

No Comments

No Known Activations