INDEX

Explanations

references to ambiguity and complexity in narratives

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

 Dude

-0.14

POCH

-0.14

aben

-0.14

erval

-0.14

ÑĢÑı

-0.14

Ped

-0.14

ectomy

-0.14

KEY

-0.13

ieu

-0.13

ome

-0.13

POSITIVE LOGITS

.Cast

0.15

 Stard

0.15

dec

0.15

laus

0.14

 printable

0.14

imus

0.14

Trader

0.13

à¸ĺ

0.13

_STRUCT

0.13

ãĤ

0.13

Activations Density 0.003%

references to ambiguity and complexity in narratives

No Comments

No Known Activations