INDEX

Explanations

relational phrases indicating connections and comparisons between entities and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

omp

-0.16

arak

-0.15

ARAM

-0.15

kla

-0.14

achts

-0.14

Î

-0.14

\.

-0.14

imps

-0.14

ìľµ

-0.13

 letzten

-0.13

POSITIVE LOGITS

het

0.18

ÑĨÐ¾Ð²

0.17

ittle

0.16

_semaphore

0.15

het

0.15

ahoma

0.15

Ãºn

0.15

uraa

0.15

 Oliv

0.15

_defaults

0.14

Activations Density 0.042%

relational phrases indicating connections and comparisons between entities and events

No Comments

No Known Activations