INDEX

Explanations

references to time indicators and sequences 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÄįÃŃ

-0.15

áºŃm

-0.15

 addCriterion

-0.14

 Ð²Ð´

-0.14

incip

-0.13

Ð°ÑĤÐµÐ¼

-0.13

Ð¾ÐºÑĢÐµÐ¼Ð°

-0.13

uter

-0.13

ìł¸

-0.13

ÃĹ↵↵

-0.13

POSITIVE LOGITS

lint

0.15

.general

0.14

hle

0.14

adays

0.13

 sens

0.13

enco

0.13

hips

0.12

.setContentType

0.12

 civilizations

0.12

çİ

0.12

Activations Density 0.191%

references to time indicators and sequences in narratives

No Comments

No Known Activations