INDEX

Explanations

proper nouns, especially names of authors and characters in literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

.fast

-0.14

.vec

-0.14

>ID

-0.14

adaki

-0.14

Ú¯Ø§ÙĨ

-0.14

 ubiquitous

-0.13

%X

-0.13

otre

-0.13

akan

-0.13

.failure

-0.13

POSITIVE LOGITS

pty

0.15

verter

0.15

 Commod

0.15

 assim

0.15

setattr

0.14

 bast

0.14

phins

0.14

imp

0.14

Ã±o

0.13

heavy

0.13

Activations Density 0.050%

proper nouns, especially names of authors and characters in literature

No Comments

No Known Activations