INDEX

Explanations

references to time and relationships in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

walker

-0.15

 Phase

-0.14

gba

-0.14

Phase

-0.14

ahas

-0.14

vel

-0.14

 lÃ²ng

-0.14

audi

-0.13

 phase

-0.13

ask

-0.13

POSITIVE LOGITS

orer

0.15

Ø±ÙĪØ¨

0.14

 wild

0.14

IENTATION

0.14

adem

0.14

omon

0.13

 -------------------------------------------------------------------------

0.13

rip

0.13

Activations Density 0.334%

references to time and relationships in a narrative context

No Comments

No Known Activations