INDEX

Explanations

negations or expressions of absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 rallying

-0.15

sep

-0.14

ione

-0.14

chor

-0.14

resco

-0.14

 processes

-0.13

Sep

-0.13

 Verd

-0.13

erez

-0.13

_resolve

-0.13

POSITIVE LOGITS

ĺ

0.15

amic

0.15

Bor

0.15

emet

0.14

ults

0.14

lisi

0.14

odb

0.14

ople

0.14

 ÐĳÐ¾ÑĢ

0.14

 antis

0.14

Activations Density 0.169%

negations or expressions of absence

No Comments

No Known Activations