INDEX

Explanations

references to geographical locations, specifically mountains and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

èĲ½

-0.15

STALL

-0.14

ndl

-0.14

ÙĪØº

-0.14

ilihan

-0.14

oce

-0.14

ÅĽcie

-0.14

ollar

-0.14

iral

-0.14

ë¦¿

-0.14

POSITIVE LOGITS

aine

0.26

aint

0.25

 Sinai

0.23

ains

0.21

pleasant

0.20

 Pleasant

0.20

 Vernon

0.17

 Carm

0.17

 pleasant

0.17

ainer

0.17

Activations Density 0.013%

references to geographical locations, specifically mountains and their variations

No Comments

No Known Activations