INDEX

Explanations

verbs and auxiliary verbs indicating past or completed actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

urum

-0.17

isco

-0.16

leston

-0.15

ichte

-0.15

chner

-0.15

PD

-0.15

ISCO

-0.14

inoa

-0.14

íĩ´

-0.14

cht

-0.14

POSITIVE LOGITS

 Hancock

0.17

IFEST

0.16

bow

0.16

thesis

0.15

omet

0.14

ims

0.14

arium

0.14

åĤ·

0.14

 Handy

0.14

 Bowling

0.14

Activations Density 0.005%

verbs and auxiliary verbs indicating past or completed actions

No Comments

No Known Activations