INDEX

Explanations

references to personal experiences and roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĤÐ¾Ñĩ

-0.14

arme

-0.14

jid

-0.14

 Attendance

-0.14

LB

-0.14

chine

-0.14

-SA

-0.13

fen

-0.13

zyst

-0.13

ombat

-0.13

POSITIVE LOGITS

arez

0.17

Å¡ov

0.15

ripp

0.15

paged

0.14

cq

0.14

ournal

0.14

agara

0.14

leur

0.14

ICLE

0.14

é«ĺéĢŁ

0.14

Activations Density 0.036%

references to personal experiences and roles in various contexts

No Comments

No Known Activations