INDEX

Explanations

phrases indicating authoritative claims or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Honest

-0.17

 field

-0.16

on

-0.15

how

-0.15

gp

-0.15

 Field

-0.14

feld

-0.14

ugo

-0.14

 armed

-0.14

 onto

-0.14

POSITIVE LOGITS

 ÙģØ¥ÙĨ

0.18

$MESS

0.15

/*č↵

0.15

amber

0.15

PickerController

0.15

OffsetTable

0.14

EATURE

0.14

EMPLARY

0.14

rine

0.14

Activations Density 0.037%

phrases indicating authoritative claims or observations

No Comments

No Known Activations