INDEX

Explanations

references to specific districts or administrative divisions

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

ertest

-0.15

jour

-0.15

itates

-0.14

anuts

-0.14

erer

-0.14

films

-0.14

idla

-0.14

aign

-0.14

ktop

-0.14

alez

-0.14

POSITIVE LOGITS

wide

0.41

-wide

0.38

-level

0.34

-Level

0.29

Wide

0.27

/Area

0.27

/state

0.27

 wide

0.26

 boundaries

0.26

 level

0.26

Activations Density 0.044%

references to specific districts or administrative divisions

No Comments

No Known Activations