INDEX

Explanations

references to physical locations or settings within narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÑĶÐ¼

-0.17

ÙĬÙĩ

-0.16

egend

-0.14

ospel

-0.14

chant

-0.14

utura

-0.14

 Ð²Ð½ÑĥÑĤÑĢÐ¸

-0.14

aga

-0.14

-0.13

ãĥ³ãĥĲãĥ¼

-0.13

POSITIVE LOGITS

 ÙĪÙģÙĬ

0.19

esson

0.15

hani

0.15

ukkit

0.15

ognito

0.15

kuk

0.14

/on

0.14

wer

0.14

ube

0.14

isson

0.14

Activations Density 0.779%

references to physical locations or settings within narratives

No Comments

No Known Activations