INDEX

Explanations

attributes of language, particularly the characteristics and classifications of words and grammar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥ¼ãĥ

-0.17

ezier

-0.16

ucker

-0.14

inalg

-0.14

ivre

-0.14

è¨

-0.14

imed

-0.14

kili

-0.14

ovÃŃ

-0.14

POSITIVE LOGITS

 tatto

0.14

mÃ®

0.14

ifacts

0.14

 Plate

0.14

 crack

0.14

klu

0.13

isha

0.13

_NOTIFY

0.13

Afr

0.13

_plain

0.13

Activations Density 0.108%

attributes of language, particularly the characteristics and classifications of words and grammar

No Comments

No Known Activations