INDEX

Explanations

sentences that express uncertainty or conditional statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

affen

-0.15

ìłľ

-0.15

odium

-0.15

oot

-0.15

inch

-0.14

odiac

-0.14

pha

-0.14

kla

-0.13

deaux

-0.13

JECTED

-0.13

POSITIVE LOGITS

 depending

0.18

 ranging

0.17

depending

0.17

ãĤ¹ãĥ¬

0.16

some

0.16

 dependent

0.16

 some

0.16

lage

0.15

ult

0.15

variation

0.15

Activations Density 0.166%

sentences that express uncertainty or conditional statements

No Comments

No Known Activations