INDEX

Explanations

phrases indicating ease or simplicity in actions or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

prot

-0.16

rganization

-0.15

 prot

-0.15

rots

-0.14

mtree

-0.14

bower

-0.14

mts

-0.14

(æľ¨

-0.14

gfx

-0.14

umpt

-0.13

POSITIVE LOGITS

uela

0.17

bru

0.16

çĴĥ

0.16

aus

0.15

oftware

0.15

anger

0.15

apat

0.15

ause

0.14

ental

0.14

(er

0.14

Activations Density 0.033%

phrases indicating ease or simplicity in actions or tasks

No Comments

No Known Activations