INDEX

Explanations

occurrences of the token "ap" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.32

-0.30

-0.28

hue

-0.27

hq

-0.27

hod

-0.26

hoff

-0.25

hud

-0.25

an

-0.24

POSITIVE LOGITS

plied

0.32

lace

0.27

plies

0.26

ort

0.24

lan

0.24

erture

0.24

artment

0.23

ta

0.23

pliance

0.23

pler

0.23

Activations Density 0.026%

occurrences of the token "ap" in various contexts

No Comments

No Known Activations