INDEX

Explanations

phrases related to managing or achieving tasks and outcomes

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

ardon

-0.17

iche

-0.16

akin

-0.15

loo

-0.14

icina

-0.14

uff

-0.14

asl

-0.14

mic

-0.14

ophon

-0.14

edBy

-0.14

POSITIVE LOGITS

 somehow

0.16

iasm

0.16

 somew

0.15

Ä±lmasÄ±

0.15

 ç¯

0.15

dut

0.14

-ÑĤÐ°ÐºÐ¸

0.14

 craft

0.13

spd

0.13

Activations Density 0.050%

phrases related to managing or achieving tasks and outcomes

No Comments

No Known Activations