INDEX

Explanations

negative statements or terms that imply negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ockey

-0.16

orry

-0.15

bung

-0.15

icom

-0.14

IPS

-0.14

ection

-0.14

 Markus

-0.14

á¿¦

-0.14

_IMPLEMENT

-0.14

phy

-0.14

POSITIVE LOGITS

Äįer

0.16

zek

0.16

ÑģÑĤÐ¸ÑĤ

0.15

ovol

0.14

anz

0.14

eto

0.13

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

0.13

tid

0.13

rag

0.13

ÙĥØ±

0.13

Activations Density 0.000%

negative statements or terms that imply negation

No Comments

No Known Activations