INDEX

Explanations

keys and references to critical objects or concepts

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

edral

-0.16

oÅ¡

-0.15

gend

-0.15

Newton

-0.14

hower

-0.14

etu

-0.14

wed

-0.13

_PHYS

-0.13

CPI

-0.13

 strokes

-0.13

POSITIVE LOGITS

ilyn

0.17

IMS

0.17

_nullable

0.15

_reporting

0.15

.bits

0.14

FAULT

0.14

radu

0.14

Ø¨ÙĪØ§Ø³Ø·Ø©

0.14

bulk

0.14

ì¦

0.14

Activations Density 0.000%

keys and references to critical objects or concepts

No Comments

No Known Activations