INDEX

Explanations

references to help or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 tane

-0.18

panse

-0.17

nten

-0.16

issance

-0.15

ledge

-0.15

clud

-0.15

ieux

-0.15

ched

-0.15

Sho

-0.15

isse

-0.15

POSITIVE LOGITS

lessly

0.19

 Äĳá»¡

0.19

desk

0.18

anca

0.15

lessness

0.14

osit

0.14

native

0.13

fully

0.13

/disable

0.13

fulness

0.13

Activations Density 0.040%

references to help or assistance

No Comments

No Known Activations