INDEX

Explanations

terms related to passengers and passenger transport

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

soever

-0.16

aber

-0.16

rray

-0.16

ÎºÎ¹

-0.15

obraz

-0.14

enda

-0.14

mens

-0.14

cky

-0.14

sel

-0.14

-ÑĤÐ¾

-0.14

POSITIVE LOGITS

hip

0.16

umn

0.15

vise

0.15

hood

0.15

bara

0.15

bilt

0.15

RIC

0.14

stva

0.14

abei

0.14

ream

0.14

Activations Density 0.012%

terms related to passengers and passenger transport

No Comments

No Known Activations