INDEX

Explanations

prepositions and conjunctions used to indicate relationships between ideas and actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bu

-0.18

inner

-0.15

jl

-0.15

Ø±Ø§

-0.15

zc

-0.14

ss

-0.14

angan

-0.14

onga

-0.14

eu

-0.14

bb

-0.14

POSITIVE LOGITS

Hib

0.17

ocab

0.17

createClass

0.16

deaux

0.15

DOI

0.15

ãģĵãģĨ

0.14

NECT

0.14

GLOSS

0.14

edx

0.14

elper

0.14

Activations Density 0.522%

prepositions and conjunctions used to indicate relationships between ideas and actions

No Comments

No Known Activations