INDEX

Explanations

phrases relating to capability and decision-making

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lobal

-0.15

 scramble

-0.14

ANE

-0.14

 global

-0.13

TES

-0.13

Sle

-0.13

re

-0.13

POSITIVE LOGITS

.inflate

0.15

bay

0.15

çĪ

0.15

ÑģÐ°

0.14

ullo

0.14

Tomorrow

0.14

alk

0.14

áº¿p

0.14

Ø§ÙĪÛĮ

0.14

andro

0.13

Activations Density 0.001%

phrases relating to capability and decision-making

No Comments

No Known Activations