INDEX

Explanations

the use of the term "exact" 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iesel

-0.21

loub

-0.15

LOPT

-0.14

jc

-0.14

strate

-0.14

ORG

-0.14

radu

-0.14

ãĤ´ãĥª

-0.14

hle

-0.14

POSITIVE LOGITS

itude

0.25

 exact

0.20

mente

0.17

 exactly

0.17

ively

0.17

ãĤ¦ãĥĪ

0.17

iveness

0.16

Exact

0.16

ITUDE

0.16

Activations Density 0.018%

the use of the term "exact" in various contexts

No Comments

No Known Activations