INDEX

Explanations

numerical values and references to thresholds in contexts of decision-making or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

IVATE

-0.17

iasi

-0.15

yny

-0.15

ivism

-0.14

ioni

-0.14

_md

-0.14

arms

-0.14

ichel

-0.14

iros

-0.14

iams

-0.14

POSITIVE LOGITS

if

0.29

If

0.28

.if

0.24

If

0.23

_if

0.21

 failure

0.21

 wenn

0.20

 náº¿u

0.20

-if

0.20

ï¼Įå¦Ĥæŀľ

0.20

Activations Density 0.152%

numerical values and references to thresholds in contexts of decision-making or assessment

No Comments

No Known Activations