INDEX

Explanations

terms related to nourishment and replenishment

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

zial

-0.18

akers

-0.17

IEW

-0.16

Â¤Â¤

-0.16

lere

-0.15

mpjes

-0.15

racat

-0.15

UAL

-0.15

ulado

-0.15

chandle

-0.15

POSITIVE LOGITS

ishing

0.57

ished

0.52

ishment

0.51

ishes

0.44

ish

0.43

ishments

0.41

isher

0.40

ISHED

0.35

ISH

0.31

ishi

0.30

Activations Density 0.017%

terms related to nourishment and replenishment

No Comments

No Known Activations