INDEX

Explanations

conditional phrases discussing situations and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

utzer

-0.17

 phys

-0.15

ib

-0.15

illo

-0.14

kos

-0.14

ãģ£ãģ¨

-0.14

_dd

-0.14

erule

-0.13

estroy

-0.13

Jug

-0.13

POSITIVE LOGITS

fal

0.17

0.15

.Utilities

0.15

Ð¸ÑģÑĮ

0.15

pei

0.14

 naopak

0.14

 Democr

0.14

.gs

0.14

á»ĳ

0.14

rÃ¡l

0.14

Activations Density 0.075%

conditional phrases discussing situations and behaviors

No Comments

No Known Activations