INDEX

Explanations

phrases that express skepticism or critique about common beliefs and notions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.15

iards

-0.15

care

-0.14

ARRANT

-0.14

fc

-0.14

iot

-0.14

POSITIVE LOGITS

edy

0.18

udy

0.17

ewis

0.16

olini

0.16

erras

0.15

.experimental

0.15

agini

0.14

enthal

0.14

VF

0.14

 obvious

0.14

Activations Density 0.122%

phrases that express skepticism or critique about common beliefs and notions

No Comments

No Known Activations