INDEX

Explanations

fragments of text that indicate uncertainty or ambiguity

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

ehr

-0.15

istrate

-0.14

bil

-0.14

uddy

-0.13

jit

-0.13

æľĭ

-0.13

ç»ı

-0.13

eln

-0.13

ÙĤØ·

-0.13

Ã³t

-0.13

POSITIVE LOGITS

bern

0.18

 UIStoryboard

0.16

anke

0.16

 learn

0.15

vara

0.15

 pokus

0.14

kÃ¡nÃŃ

0.14

lessons

0.14

uran

0.14

.obtain

0.14

Activations Density 0.108%

fragments of text that indicate uncertainty or ambiguity

No Comments

No Known Activations

fragments of text that indicate uncertainty or ambiguity

No Comments

No Known Activations