INDEX

Explanations

terms related to problem-solving and solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ively

-0.18

ests

-0.15

ently

-0.15

ily

-0.15

ically

-0.14

ainty

-0.14

ãĥªãĥ¼ãĤº

-0.14

 Pret

-0.14

orts

-0.14

POSITIVE LOGITS

ated

0.24

ando

0.18

ato

0.18

aticon

0.18

ating

0.17

ado

0.17

CLS

0.17

anto

0.17

ative

0.16

aciÃ³n

0.16

Activations Density 0.077%

terms related to problem-solving and solutions

No Comments

No Known Activations