INDEX

Explanations

references to household items and activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

strup

-0.16

-0.15

rir

-0.14

icle

-0.14

ogan

-0.14

 followed

-0.14

 Leban

-0.14

-0.13

urai

-0.13

emu

-0.13

POSITIVE LOGITS

ertools

0.16

ooks

0.16

Ded

0.15

spark

0.15

ipa

0.15

ìļ©

0.15

-grade

0.15

ÑĪÐµÐ¼

0.15

nah

0.15

ORIES

0.14

Activations Density 0.330%

references to household items and activities

No Comments

No Known Activations