INDEX

Explanations

phrases that convey effort or skill in achieving tasks

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

 herself

-0.16

bers

-0.15

ewan

-0.14

è¾

-0.14

ESC

-0.14

ont

-0.14

ioso

-0.13

esc

-0.13

avou

-0.13

POSITIVE LOGITS

elson

0.17

stamp

0.15

æı

0.15

Ð¸Ð½Ð¾Ð²

0.15

edis

0.15

 Prism

0.15

uci

0.14

 Redistributions

0.14

ÙĬØ¯Ø§

0.14

ohn

0.14

Activations Density 0.026%

phrases that convey effort or skill in achieving tasks

No Comments

No Known Activations