INDEX

Explanations

frequent auxiliary verbs and forms of "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Bast

-0.15

_cid

-0.14

onte

-0.14

dfd

-0.14

her

-0.14

mens

-0.14

uko

-0.14

 subur

-0.13

ici

-0.13

none

-0.13

POSITIVE LOGITS

utta

0.15

unken

0.15

vais

0.15

egan

0.15

0.14

raid

0.14

à¹Īà¸²à¸Ļ

0.14

uper

0.14

 Rogue

0.14

éĽ²

0.14

Activations Density 0.003%

frequent auxiliary verbs and forms of "to be."

No Comments

No Known Activations