INDEX

Explanations

repeated references to personal identity and involvement in actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

asso

-0.17

cock

-0.16

GetMethod

-0.14

Č↵

-0.14

wise

-0.14

rompt

-0.13

Par

-0.13

 Schmidt

-0.13

ABB

-0.13

eyer

-0.13

POSITIVE LOGITS

iew

0.17

onec

0.15

iciel

0.14

-uri

0.13

amedi

0.13

ibrator

0.13

 Favor

0.13

LING

0.13

amer

0.13

mers

0.13

Activations Density 0.198%

repeated references to personal identity and involvement in actions

No Comments

No Known Activations