INDEX

Explanations

expressions of typicality and comparisons within contexts

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

incr

-0.15

OfSize

-0.15

ulin

-0.15

imo

-0.15

hod

-0.15

ijk

-0.14

ullo

-0.14

avigation

-0.14

à¸²à¸Ļ

-0.14

quiz

-0.14

POSITIVE LOGITS

mdb

0.16

ensch

0.15

ufen

0.14

clerosis

0.14

.toObject

0.14

 Ø¬Ø¯Ø§

0.14

IFn

0.14

-IS

0.13

.vars

0.13

 occasion

0.13

Activations Density 0.045%

expressions of typicality and comparisons within contexts

No Comments

No Known Activations