INDEX

Explanations

instructions or requests related to checking information and taking actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ansi

-0.18

imo

-0.15

anson

-0.14

lane

-0.14

edian

-0.14

Lyn

-0.14

Dod

-0.14

Lia

-0.14

oleon

-0.14

POSITIVE LOGITS

strcasecmp

0.18

ë§¥

0.16

Ãªu

0.16

operands

0.15

 Äĳá»

0.15

abcdefghijkl

0.15

_ASSUME

0.15

ocate

0.14

 intptr

0.14

neys

0.14

Activations Density 0.079%

instructions or requests related to checking information and taking actions

No Comments

No Known Activations