INDEX

Explanations

phrases indicating negative outcomes or warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ãĤ·ãĥ¼

-0.16

vie

-0.15

icken

-0.14

Ø¨Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.14

Digits

-0.14

iki

-0.14

AAF

-0.14

 Sakura

-0.14

 Markus

-0.14

vi

-0.14

POSITIVE LOGITS

idge

0.15

hani

0.15

ISTA

0.15

Å¾

0.15

hurst

0.14

zier

0.14

itle

0.14

ubern

0.14

 oppon

0.14

Activations Density 0.032%

phrases indicating negative outcomes or warnings

No Comments

No Known Activations