INDEX

Explanations

phrases indicating intention or desire to go somewhere or do something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

use

-0.16

loom

-0.15

ynchronized

-0.15

phans

-0.15

ldr

-0.14

ixa

-0.14

tics

-0.14

ãĥ³ãĥĶ

-0.14

xes

-0.14

jax

-0.13

POSITIVE LOGITS

ogle

0.17

redi

0.16

cott

0.15

ishi

0.15

ehler

0.14

à¸²à¸ĺ

0.14

ebb

0.14

çłĤ

0.14

EFR

0.13

ornment

0.13

Activations Density 0.068%

phrases indicating intention or desire to go somewhere or do something

No Comments

No Known Activations