INDEX

Explanations

names and references to individuals, particularly in the context of death and obituaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ahir

-0.15

enberg

-0.14

bung

-0.14

alus

-0.13

assis

-0.13

ViewControllerAnimated

-0.13

_FORWARD

-0.13

aryawan

-0.13

ovo

-0.13

.mvp

-0.13

POSITIVE LOGITS

 ilma

0.16

IALOG

0.15

à¸Ľà¸£à¸°

0.15

roller

0.15

.nlm

0.14

 rolls

0.14

RN

0.14

avn

0.14

.TabIndex

0.14

Activations Density 0.182%

names and references to individuals, particularly in the context of death and obituaries

No Comments

No Known Activations