INDEX

Explanations

references to specific locations or details in descriptions

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

 Leone

-0.14

aso

-0.14

expiry

-0.13

avenport

-0.13

uci

-0.13

anium

-0.13

ova

-0.13

 Beled

-0.13

ucc

-0.13

Äįan

-0.13

POSITIVE LOGITS

Ã¶ff

0.16

ISS

0.15

Gir

0.14

atori

0.14

ptest

0.14

Å¥

0.13

_SN

0.13

iento

0.13

translator

0.13

Activations Density 0.258%

references to specific locations or details in descriptions

No Comments

No Known Activations