INDEX

Explanations

first-person references and pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ondo

-0.16

pivot

-0.15

ala

-0.15

Ð½ÑĸÐ¿

-0.14

amon

-0.14

ìĪł

-0.14

PointF

-0.14

 Bernstein

-0.14

ollar

-0.14

ifax

-0.13

POSITIVE LOGITS

opo

0.15

ÏĢÏĮ

0.15

aki

0.14

quam

0.14

rup

0.14

Î³Î¹

0.14

 baise

0.14

ÏĢÎ¿Î½

0.14

Å¾

0.14

Activations Density 0.075%

first-person references and pronouns

No Comments

No Known Activations